Extra Credits I Would like to see a Game in the Future that uses real, Self-learning A.I. Imagine For example a Game like Battlefield where a "Black Knight" A.I. Joins every few Games and changes the way the Players have to behave in that Match by simply being to Strong For one player to Deal with Or a new Game Mode: the player-Horde against the A.I. Ninja A good example is the bossfight Mode from Robocraft, where one player can Build an Robot with 10 Times the strength of the Enemy players
the competition isnt that hard when fucking jenna marbles is in fourth place. Still, congratulations. I just thought a show of this quality would deserve a higher award than just this.
Yeah, I thought a lot of Time's choices were questionable too. There's a ton of channels (like Game Theorists) that should've been mentioned before vlog crap
I always loved the moment when someone died in Skyrim and people in the street or there friend reacted to it. This is AI that doesn't lead to me making a decision, but it's still important because it furthers the immersion!
An AI that is super good will frustrate the player, leading to him, eventually (be either on purpose or not), to find ways to put the AI in a situation where it was not mean to be, in turn, leaving the AI to look as it was poor, that of course, if the player doesn't leave the game first. In the end, the player will remember the encounter, not because it was memorable but because it was bad; as such, you want to challenge the player, entertain him, not show him who is best.
Not really, even if your NPC is unbeatable by lore, it should not affect the way the encounter is played off, if you are forcing the player to fight you should still provide a memorable encounter, take the first boss of Megaman X or Metal Gear Rising, both of them are "unbeatable" and yet you still have a win condition, and both battles serve a purpose, but if you're just going to dust off the player on the first hit you may as well do it in a cutscene, otherwise the player may feel cheated. Also by entertaining, I don't mean easy, I mean it has to provide fun to the player, it can be simple or complex, easy or hard, but not just plain unfair. If your NPC is supposed to be the best of the best of the best, of course, it makes sense to make him challenging, and that's the thing, there's a clear difference between testing the skill of a player and abusing your systems to make a battle artificially hard. As an example, the last boss of AceCombat:AH is supposed to be a very skilled pilot, so skilled in fact that it will teleport to the back of the player most of the time, making the battle artificially hard and unfair regardless of your skill level.
I'm a machine learning researcher, and I'm wondering what the future of machine learning in games is? How does a true AI, trained with whatever goals it may have, change the relationship between players and NPCs? Is it a good idea for all games to implement this, for all games to do it? I'd love to see an episode on this, especially in light of the news about Dota 2.
One place where i think machine learning would excel is rougelikes, because the ai would be different for every game too, whle also consistnelty making each run much interesting
Machine learning has a few more specific uses, one is to learn the players patterns so it can predict and become harder, so both the player and the ai become better with time, making the game always challenging. The second one is so the player cant exploit anything in game, haveing an ai assess the players spam choices to see if there is an issue and stop the them from doing it so the players are forced to always find different and creative ways to play the game. I'd say those are the main uses for it
I can say for sure machine learning is not good for all game. If not very carefully crafted, a machine learning AI could become impossible to beat, which totally counter the purpose of an AI. There are here to be beaten. Also, most game have no use of machine learning just because, as said in the video, sometime a simple AI is more than enough. Take a racing game for exemple, an AI in a racing game need to follow the optimal trajectory, and go just fast enough to provide a challenge to the player. Yes you could use machine learning so the AI could learn the optimal trajectory, or you could just program the trajectory directly, which will take less time and ressources.
Also, its decided whether to use mechine learning or not depending on the mechanics in the game, depending on how you designd a game it can become harmful to the gameplay, i dont quite remember the name of the game but there was one that you played as a god and you interacted with the world through a chosen avatar, that you commanded and slowly it learned on how to automatically act when an event ocurred, but towards the middle of the game there were so many commands and changes on player interaction that the ai got confused and started to ruin the game. It is a very dangerous to choose to have machine learning in a game, specially because it takes too long to see how it turns out that when its finished, you dont have time to go back and start again if it goes wrong
Don't forget, an AI can react in 1 frame, probably 0 frames. It's more likely they're sometimes told to wait for you to do something and respond instantly as though they had predicted it.
I hate the Smash 4 AI exactly for that. All those frame-perfect reactions actually kill the fun. Mind-game strategies like baiting are of no use, all you can do is go for safe moves, punish their moves, or hope they decide not to dodge your attacks.
I can only imagine if my A.I. companions felt like I was playing favorites, and acted different in response, or if one of the enemy A.I., upon seeing me point my gun at them but not fire, decided to try reasoning with me, rather than shoot and surely die, or something else along those lines.
It looks like there are a lot of ppl who'd like to see less mourderous enemies and less friendly friends. A companion leaving the party becouse you didn't engage with them? A regular trooper joining your epic quest out of desperation? I'd love to see that in a big production one day.
András Fogarasi This is actually a big issue with AIs for board games like chess. It is most fun to play these games against an opponent with a similar skill level whose thought processes can be understood and counterplayed against. Therefore, having the most powerful AI is actually not a benefit, as AIs play chess differently from humans (because they do tree searches rather than heuristics). Often, chess programs will simply give the AI less time to run and call that the "easier" difficulty setting, which doesn't make the AI moves any more understandable. I am hoping that the AI architecture used in AlphaGo can change this. High level Go players have reported that AlphaGo has a distinct "style" of play - that it has a "personality". And its value and policy network architecture definitely _feels_ like how humans learn these games.
Rad¡o Head nothing specific, but when you have to lead someone from point A to point B as a quest, and the AI is so bad that that they end up walking into walls and can't get through doorways.
Well you know I think some cases more life-like AI may be better. Like in skyrim where people have a schedule, some kind of disision tree swapping, or when you get 2 ai next to each other and they start talking.
How complex and in what will the AI be complex in is completely dependable on what genre and type of gameplay you are going for with the game, if not thought thoroughly it can destroy the gameplay
The two cases you described are not complex situations, they are referring to the kind of AI the game uses when the player interacts with NPC's, a schedule or interaction between NPC's is not always that complex (it may look like it is, but most of the time is not).
Hi Kabloosh! Currently there is not any formal method of guaranteeing that a viewer-suggested topic will be featured on Extra Credits (the way that Extra History topics can be suggested and voted on). Most people just tweet/email/message us about their ideas anyway. We do read them all!
Extra Credits I know it is ironic to reply to this comment with a request but I have an interesting topic. How do fanbases affect games. For example Minecraft and undertale
It's hard as fuck but go for it. Study up on mathematics (particularly calculus and algebra). Then go for discrete math and algorithms. Programming is also a must at some point. Then you can get directly into the meat of it.
I'm actually already a graduate of computer science and game design from my university, it's just that I can't make AI work my first job, i'm not prepared as most of my work hasn't required much AI, so I don't have any AI work to show on a portfolio (working to resolve that)
DemonGrenade274 I disagree. You certainly will need such knowledge for game development in general, but not for AI in particular. Like this video says, AI isn't as difficult or scary as you think. The scarier the prospect of creating that AI, the worse that AI will almost certainly be, especially for a Monster Hunter or Dark Souls style game. There will be no machine learning or neural networks here (I feel I should note that AI in games is very different from AI in education or research). You can always make an AI simpler by mimicking real choice with a decision tree and a bit of RNG for flavor, for most games no one will know the difference. In terms of decision making, it mostly just comes down to a tree of decisions that it makes periodically. If player behind me, do tail swipe. If player in front and close, do bite. If player in front and far, breath fire. That kind of thing. If you wanted to add a bit of variety in, you simply roll an RNG and make a choice based on that. If player behind me and rolled 0, tail swipe; if player behind me and rolled 1, tail slam. Actually implementing the attacks or movements goes beyond AI itself (though it is notable "Video Game AI" is not a full job on its own, it is simply part of being a game dev :P) Regardless, the key thing to remember is that, in general, what you really want is an AI that _appears_ to be smart. You don't want to try to actually make it smart, it will usually just end up a lot dumber for the effort. Oh, and I would be remiss not to mention Ellie from The Last of Us and Elizabeth from Bioshock Infinite as good examples of AI that can appear smart in a variety of ways, and yet are still far simpler than their choices seem. I think the Bioshock one even has a video of the devs discussing it somewhere... I'll leave you to look for it on your own though.
Geoffrey Perrin I'd love to do computer science and chemistry and zoology when I graduate ( I know it's not the year 1500 where that would be really possible even computer science) but I feel like the public doesn't see science and I can't explain it and I've been wanting to make a game where the ai re able to build and learn a kind of mid evil based game and it's kind of a experiment to see if a ai can out class a human at building a successful civilization.
An interesting question regarding AI: how do developers make it bad at stuff? For example, I throw my grenade at the bad guy. Sometimes, they're not quick enough to dodge away before being blown up. Or their aim is off when attacking you. What goes into deciding how often the bad guy tries and fails to accomplish what is in its decision tree?
A term I have heard regarding shooters is: "Designing a perfect AI is easy, making it beatable and realistic is the hard part." I can why it would be the case. The perfect playing AI always hits a headshot the moment it can see the player, but that is hardly fair or fun. Delays and variables need to be a part of it.
It might have been on this channel or another similar one, but I heard that in the Uncharted games the AI is programmed to always miss you for a specific amount of time after you come out of cover.
A very interesting question. After all if the AI in a shooter game actualy worked at 100% of it's capasity then every enemy would literaly BE an aimbot.
Hello! Game AI Programmer here! Just figured that I'd mention the thing about behaviour trees driving an AI isn't strictly always true. Behaviour Trees are definitely the most common one, and very powerful, but they work on a very "yes" and "no" basis, but sometimes that isn't powerful enough, for games like RTS's. There's a bunch of ways to implemented this, like Utility Based Reasoning, to work in a much more fluid way. It makes it much less predictable, but for some games that's what you want. Anyways, just thought I'd throw out there that Behaviour Trees aren't the be-all and end-all! Thanks for the video, have a great day to anyone reading!
I think a great example of this is Dark Souls AI. It's often predictable, intuitive and exploitable, but it's always engaging. There's just something about fighting a Dark Souls enemy that's fundamentally engaging.
Please come back to this! I work in a GAME in the UK and your show helps me to do the work I love and enriches my understanding of my favourite hobby. Please never stop.
How does this apply to CPU players in fighting games and RTS's? I would think that in that scenario a more complicated AI is the better option so that a player can play possibly thousands of variations of the same scenario (eg. Fox only no items Final Destination) and still see new outcomes.
I just considered that because I am far less engaged in a game when I have a general sense of what the AI is going to do, which is the exact opposite purpose of AI as they stated. Even when I play an FPS I'd rather not know what would happen, but instead make assumptions that could be wildly off base and improvise when that occurs.
Not necessarily complex AI but many different AIs. The worst thing for an RTS is for every faction/side to behave the same regardless of how complex that behaviour is.
Not exactly complex, but it does need a good learning pattern ai, it doesn't need to make complex decisions, but it needs to read the players movements and move accordingly, forcing the player to change the strategy used.
Stephen von Schulmann you got a point. More complexity in the cpu make the game Harder and more fun to discover. Fighting a lvl 9 fox would be very borring if you could read every reaction
I had a discussion a while ago with a friend about this. He said that games had working low-level AIs, I said that those were only decission tree's disguised to look like AIs. He told me then that those decission trees were the AIs, that all form of interaction with a world, being an ant, a human or game AI were a result of decissions, just with different levels of complexity.
Very interesting episode! I'd say there's definitely a time and place for complex AI, but sometimes it just might not be that time nor place. Also, I would definitely be interested in an episode about AI impacting the emotional experience!
emotional can be had at even really basic AI.... I had a guard in Hl1 survive a encounter against a hostile Marine and well I did what I could to escort said guard to safely (or a ladder). ((the security guard even whit there crappy pistil could still kill a marine in a 1 vs 1 if the fight was on mid range mostly becos the guard had better aim)).. the short range and the marine won all the time.
I don't even play video games all that often (MAYBE once a week for two hours) but you guys just have such engaging content that I keep watching these videos like an addict. Thanks for making RUclips better!
"When we talk about AI in games, we're not really talking about artificial intelligence. We are talking about decision trees" made me shudder. There are lots of different types of ai in games. Decision trees are not even the only type of expert system in games. One of the most common AI in games traditionally was decision trees. Nowadays there are all sorts of AI from bleeding edge neural networks, to heuristics like the A Star algorithm, to even cellular automata.
Add finite state machines to that list. That's another common approach. I wouldn't be surprised if there are game AI systems which use more powerful models, like pushdown automata, too.
Parts of GalCiv2 AI worked like a chess computer, using the free CPU power during players turn to calculate turns ahead and choose optimal outcomes. So the longer the player took their turn/more powerful CPU would mean more better play by the AI opponents.
I remember hearing about a game that had various 'traits' for their enemy ai. Basically, performing or observing certain actions could raise or lower variables such as 'courage', 'morale', and 'stress'. Higher courage would allow the ai to stay out of cover longer and get closer to damage sources. Lower morale would make the ai more likely to hide or avoid engaging you, and make them less likely to attempt to achieve objectives. Since the ai could adapt on the fly, it made gameplay very interesting, as you could use intimidation tactics to scare the enemy away, and the bots would constantly try to counter your tactics, requiring you to switch tactics often. Unfortunately, I don't remember the name of the game, but it was great fun the one time I played it.
Would love to see an emotional/narrative A.I video As a player, 3 examples I can think of that I have seen are: -When game music changes depending on the player state, environment, etc -A.I speech. "SQUAD NEUTRALIZE FREEMAN" -When you pull out a weapon and NPC's run or change behavior (e.g in STALKER, NPC's tell you to lower your weapon before you can speak to them)
8:05 "How does this [behaviour I am about to add] set up an opportunity for the player to make interesting decisions within the game?" Brilliant. Thank you.
I have to recognize that this particular video (and surely many more) have a really good time management, I truly felt like there was a good amount of information in a short window of time which was easy to grasp and understand. Also, I was thinking around the 4-5 minute mark that the video was about to end but there was still more left (which that is really awesome). Congrats on the good writing/directing of the video and keep at it with the good job!
This even applies to AI filling in for human players in games like Civ. One of the enjoyable thing about competing with humans is that they have complex plans but that the plans do have logic to them and if you can figure them out you can outplay them.
But how many times it actually is the case of over-engineered AI vs not enough attention paid to good AI? Most of the time AI is just god damn awful. How many times your teammates get in the way? How many times in RTS the opposing AI simply cheats instead of playing better? Etc, etc. I don't think developers need incentive not to invest in AI, as they do a fine job of it now..
Vaidas Šukaukas I think that in order for an AI to appear smart you don't really need a lot of decision paths, just don't make them DUMB. Like you said, team mates standing in the way, or in Crysis (I am playing it right now so it's a pretty specific example that I could remember) when you shoot enemies with a silencer they will just stand there instead of looking for cover
Input on the emotional interaction between player and AI would be fantastic. I've just launched my game dev crew and I'd like to give my team the chance to really focus on that aspect of a game.
Seriously I feel like I'm the only one here who doesn't work or plan on working on a game, these are just good videos that I like and they shed light on the gaming industries as unbiased as possible, good on you James and crew
oh man PLEASE come back to this. This episode was super informative and interesting but I was a little disappointed it was only about Enemy AI. hopefully this latter portion they teased is where non-enemy AI comes in. can't wait!
I'd love to see an episode on how AI can emotionally engage the player! The closest examples I can think of that is when Sif from Dark Souls starts limping and attacking slower when his health is low, or how the Fume Knight from Dark Souls 2 will go into his second phase immediately if you're wearing Velstadt's helm. Those are narratively driven events and change the fights quite a bit. But I can't think of much else.
I'm most definitely interested in hearing about the emotional and narrative utilization of game AI - as someone who wants to get into game development in the near future and create narrative-focused games, learning about any tools I could possibly use would be fantastic.
There is one thing I have to disagree with you, EC. A.I. should't be intuitive. When an A.I. is stripped of its masks and made naked by the player's eye, the singleplayer experience is dead. I bring RTS A.I. as an example of this; not the units but the enemy CPU. But it is also true with FPS, (I exploited quake2 A.I. on multiple occasions) and I bet with many more.
I see the point you are trying to make here - behaviour should be more natural and unpredictable. Yet all games from Halo to Splinter cell are all about devising a plan and then putting it to action. If you throw that grenade and the enemy runs for cover only 50% of the time then you don't get that satisfaction of being a strategic thinker. Same with guys in stealth games always annoyingly voicing their thoughts. I see many ways AI could improve while not becoming more unintuitive, reacting more diversely to more player actions is one of them. They see you carrying a shotgun - they will try to keep their distance, you broke into their compounds unseen armed with a tranquilizer gun - they will set up traps, you walked into the women's restroom - they will berate you for being a pervert. It's not in unpredictability, it's in variety, because games are solid mechanics to be conquered with diverse skills.
There is no one definitive answer. The Mario games would not benefit from unintuitive AI, in fact, they would get worse by making the AI less predictable.
Well, that´s why he said over time. If you can´t learn an AI, then it´s no better than an random number generator, because unpredictable decission mean it rarely does the best decissions. It also wouldn´t make the NPCs more lifelike, but less. In real life you learn to predict people, too. That what makes you connect with them. Someone who is completely unpredictable isn´t a good character but a psychopath. It would get even worse if those were mission critical and on your side. Remember every escort mission you ever had with a bad companion AI. Now imagine those missions with completely unpredictable companions.
That's a flawed concept for FPS's if you've actually been in any kind of fight. Plans never survive first contact, and enemies being predictable is absolutely immersion-breaking.
This is one of the reasons why games like monster hunter got under my skin. Besides the various tells the monster gives you before using an attack, there was no way to know which attack it'll do next. It makes the hunts exciting and different, but it also makes me want to murder someone with a spoon whenever it initiates an attack that is completely inescapable for me.
In fairness I think attacks like that play a big part in the "makeing interesting problems for the player" part of an AI's job in a game. While it would be frustrating to die or get screwed over by that inescapable attack the first time, on every subsequent encounter with that enemy you know they have that ability. At that point the game shifts gear from "spot the tell and react" to "figure out how to bait the AI into doing it's less anoying attacks". Heck as a SoulsBorne veteran I can say that for my own part knowing how to bait the attacks I personaly find easiest to deal with is 80% of how I beat most bosses (and even most reasonably hard enemies) in such games.
theyre only inescapable because you put yourself in the wrong position at the wrong time. one of the things i love about MH is that every single attack is completely avoidable, and its completely fair that i got smacked by it. they are hard games. very hard. but theyre just too fair.
justdontask3 While I agree, to be fair the AI is also a lot less predictable than in older games both in who they target and in choosing attacks. I think most of us run into those situations where they home in on one player or spam or chain attacks at some point. For me that was Deviljho, it followed me around a few minutes spamming its head-swipe, with the occasional boulder or body-check. I survived several close calls while the other guys sat and watched.XD
I have no idea why I enjoy these videos, but I genuinely do. My thanks to you for creating your content, even if I can't put my finger on why I enjoy it!
You guys could pitch literally any episode idea on any facet of game design and I would be hyped to learn more. I love learning how things fit together, and I love games, so even though I'm nowhere near a career in game design, It's still fascinating to learn how games are put together and then recognize those facets in the games I play. TL;DR, I'd love for y'all to do an episode on how NPC decision trees can augment the Narrative of a game, and I'll even toss the first idea of an example. In Halo, the enemy Hunters always travel in pairs, and when you kill one hunter, the second one goes berzerk and charges you to initiate a smashfest on your face. Even if you don't know exactly why they go into fury mode (It isn't what most people might think) It's easy enough to intuit that this hunter is angry over loosing it's partner. Small touches like that can add massive levels of depth and immersion to a narrative, all without a single cut scene or word of dialogue.
This goes back to your video on "Depth Versus Complexity". I would love to see more videos on game AI. Sometimes the environment is a complex AI as a whole, but is distributed through simple entities or attributes that fundamentally resonates in a granular snowball like fashion, intuitively resonating with and affecting the player in nuanced ways.
As I a soeedrunning I can say that learning how AI reacts to situations is very important for getting the game done fast and thus being enter at it, all of this is true.
This episode has been especially helpful for me as i am currently pondering on how to improve my AI for a squad tactics game im working on as a hobby project. Thanks for the help, and I'd love to see you talk more about AI!
I really like the AI companions in Star Wars: Republic Commando. Not only are they decent in combat, and very distinct in what they do, but they are also interesting with their side commentary. It makes you really enjoy them as squad mates and makes you take that extra step towards trying to get through each level together. That is good AI programing.
One thing I'd like to see used more frequently is the idea of an "AI director" overseeing the NPCs' behavior, so they're not just all autonomous units that could interfere with each other or accidentally gang up on the player in ways that are impossible to counter. Games where enemies infinitely respawn would especially benefit from systems like that.
metal gear solid 5 had NPC AI that drove my emotions. after getting spotted and trying to fight my way out of a situation I became overwhelmed and had to take cover. as i waited for everyone to stop searching for me, I was shocked to see the surviving NPCs go to each of their fallen comrades and grieve over them. suddenly, for a few seconds, these weren't just video game bad guys, they were real. it made me rethink my plan to attack when their guard was down and instead be especially careful to just sneak out undetected. this might be a good example to use when you do that video on AI driving emotional responses.
Gotta admit that, even though so many of my fav games fill into interesting AI behaviors that are simple, some of my fav experiences on non demon/alien/robot combat in games haven't been rivaled for over a decade. And that is Half Life's soldiers and FEAR's troops. The way they communicate between eachother and how elaborate (in relation to most NPCs even to this day) to how you place yourself in the map, the way you move, the way they move, your attacks and theirs, how they coordinate, haven't had as exciting firefights on any game that isn't highly exagerated on fantastical on enemy variety and attacks (which is most modern shooters) since then. PS: I freaking love the FPS Behavior char design you guys did! It's so damn adorable and I was glad you didn't show him getting killed, cause gotta admit I'd have felt sad x3
technically speaking visual novels use decision trees for emotional interaction, it just feels less organic because the player is using those same decision trees (and when it's a bit more sophisticated, like a chatbot, immersion is usually tough not always shattered)
I was going to make a comment saying "Yeah, then how does this work with your points made in your "Strategic Uncertainty" video eh?" 5 Minutes in that video, you addressed it. Kudos, very consistent haha.
For your last question... the one where you ask "how to use A.I. to increase emotional/narative engagement", I think you can find the answer (or part of it) in Mark Brown's Game Maker's Toolkit episode about "The Last Guardian". He had a happy accident while playing the game that shows how such an A.I. can work.
Awesome. I'm working on an AI series myself, so this was very helpful. Please do continue making more AI related videos, it's such an interesting field.
Many games brag about their complex enemy AI, but "complex" doesn't always mean "good." So how should we design AI?
Extra Credits Why is there 12 comments i only see 3(incluoding my own in both numbers)
Extra Credits Please make a video about PMCs ( Private Military Contractors)
Give us the instructions how to make microwave burrito please :3
The RandomQueso that's a great idea
Extra Credits I Would like to see a Game in the Future that uses real, Self-learning A.I.
Imagine For example a Game like Battlefield where a "Black Knight" A.I. Joins every few Games and changes the way the Players have to behave in that Match by simply being to Strong For one player to Deal with
Or a new Game Mode: the player-Horde against the A.I. Ninja
A good example is the bossfight Mode from Robocraft, where one player can Build an Robot with 10 Times the strength of the Enemy players
Congrats on getting featured by TIME magazine. Well deserved.
Thank you! We are all incredibly excited about it! The news was a welcome morale boost.
(For reference: time.com/4890205/best-youtube-channels)
they were no1 on their "15 youtube channels you should watch" list
link, please?
the competition isnt that hard when fucking jenna marbles is in fourth place. Still, congratulations. I just thought a show of this quality would deserve a higher award than just this.
Yeah, I thought a lot of Time's choices were questionable too. There's a ton of channels (like Game Theorists) that should've been mentioned before vlog crap
I always loved the moment when someone died in Skyrim and people in the street or there friend reacted to it. This is AI that doesn't lead to me making a decision, but it's still important because it furthers the immersion!
But sometimes you assasinate 2 drunks and the third just walks right past not caring at sll
LoTR Builders as long as you don't offer them black braier mead they will like you:D
But are they really... truly...
IMMERSIVE?
I usually assassinate someone, preferrably a bandit, and when another bandit stops and notices the corpse, I kill that bandit, too. :)
Not as ... IMERSIVE as this booty mod there are many like it but this one's the new one
Just remember guys, the job of an AI is not to destroy the player, but to entertain him.
Why not both
An AI that is super good will frustrate the player, leading to him, eventually (be either on purpose or not), to find ways to put the AI in a situation where it was not mean to be, in turn, leaving the AI to look as it was poor, that of course, if the player doesn't leave the game first.
In the end, the player will remember the encounter, not because it was memorable but because it was bad; as such, you want to challenge the player, entertain him, not show him who is best.
+Ghost Tactician Every "I wanna be the X" game ever.
Unless your Elon Musk, then the job of the ai is to destroy the best!
Not really, even if your NPC is unbeatable by lore, it should not affect the way the encounter is played off, if you are forcing the player to fight you should still provide a memorable encounter, take the first boss of Megaman X or Metal Gear Rising, both of them are "unbeatable" and yet you still have a win condition, and both battles serve a purpose, but if you're just going to dust off the player on the first hit you may as well do it in a cutscene, otherwise the player may feel cheated.
Also by entertaining, I don't mean easy, I mean it has to provide fun to the player, it can be simple or complex, easy or hard, but not just plain unfair.
If your NPC is supposed to be the best of the best of the best, of course, it makes sense to make him challenging, and that's the thing, there's a clear difference between testing the skill of a player and abusing your systems to make a battle artificially hard.
As an example, the last boss of AceCombat:AH is supposed to be a very skilled pilot, so skilled in fact that it will teleport to the back of the player most of the time, making the battle artificially hard and unfair regardless of your skill level.
That "FPS enemy" was totally adorable.
how about AI in "player-like" positions, such as CPU opponents in strategy games or fighting games, or NPC party members in certain RPGs?
"If you folks are interested..."
Well, duh. Of course, we are interested.
Isn't that why the Extra Credits to-do stack is a mile tall?
Timothy McLean Its more like a concept than a number. Because its infinite.
Somewhere James is building a Taj Mahal out of individual pages for script ideas for episodes he wants to do.
This need more UPVOTES! XD
I'm a machine learning researcher, and I'm wondering what the future of machine learning in games is? How does a true AI, trained with whatever goals it may have, change the relationship between players and NPCs? Is it a good idea for all games to implement this, for all games to do it? I'd love to see an episode on this, especially in light of the news about Dota 2.
One place where i think machine learning would excel is rougelikes, because the ai would be different for every game too, whle also consistnelty making each run much interesting
Machine learning has a few more specific uses, one is to learn the players patterns so it can predict and become harder, so both the player and the ai become better with time, making the game always challenging. The second one is so the player cant exploit anything in game, haveing an ai assess the players spam choices to see if there is an issue and stop the them from doing it so the players are forced to always find different and creative ways to play the game. I'd say those are the main uses for it
I can say for sure machine learning is not good for all game. If not very carefully crafted, a machine learning AI could become impossible to beat, which totally counter the purpose of an AI. There are here to be beaten.
Also, most game have no use of machine learning just because, as said in the video, sometime a simple AI is more than enough. Take a racing game for exemple, an AI in a racing game need to follow the optimal trajectory, and go just fast enough to provide a challenge to the player. Yes you could use machine learning so the AI could learn the optimal trajectory, or you could just program the trajectory directly, which will take less time and ressources.
Also, its decided whether to use mechine learning or not depending on the mechanics in the game, depending on how you designd a game it can become harmful to the gameplay, i dont quite remember the name of the game but there was one that you played as a god and you interacted with the world through a chosen avatar, that you commanded and slowly it learned on how to automatically act when an event ocurred, but towards the middle of the game there were so many commands and changes on player interaction that the ai got confused and started to ruin the game. It is a very dangerous to choose to have machine learning in a game, specially because it takes too long to see how it turns out that when its finished, you dont have time to go back and start again if it goes wrong
Nic Fishman
that sound like its not happening in the next 5 years, hardware requirements would probably too high
dont you hate when fighting game AIs are able to predict your moves
Derpaboop Derp "predict"
Don't forget, an AI can react in 1 frame, probably 0 frames.
It's more likely they're sometimes told to wait for you to do something and respond instantly as though they had predicted it.
Mortal Kombat 2 is notorious for this type of AI
What if...
*YOU* Are the AI‽
(Duhn-duhn-DUHN!)
I hate the Smash 4 AI exactly for that. All those frame-perfect reactions actually kill the fun. Mind-game strategies like baiting are of no use, all you can do is go for safe moves, punish their moves, or hope they decide not to dodge your attacks.
I can only imagine if my A.I. companions felt like I was playing favorites, and acted different in response, or if one of the enemy A.I., upon seeing me point my gun at them but not fire, decided to try reasoning with me, rather than shoot and surely die, or something else along those lines.
It looks like there are a lot of ppl who'd like to see less mourderous enemies and less friendly friends. A companion leaving the party becouse you didn't engage with them? A regular trooper joining your epic quest out of desperation? I'd love to see that in a big production one day.
Yeah, more chance of non-player characters changing opinions and even sides, expectantly or not as expectantly.
The problem with game AI:
It's too easy to make it perfect. Creating an aimbot is a trivial task.
András Fogarasi This is actually a big issue with AIs for board games like chess. It is most fun to play these games against an opponent with a similar skill level whose thought processes can be understood and counterplayed against. Therefore, having the most powerful AI is actually not a benefit, as AIs play chess differently from humans (because they do tree searches rather than heuristics). Often, chess programs will simply give the AI less time to run and call that the "easier" difficulty setting, which doesn't make the AI moves any more understandable.
I am hoping that the AI architecture used in AlphaGo can change this. High level Go players have reported that AlphaGo has a distinct "style" of play - that it has a "personality". And its value and policy network architecture definitely _feels_ like how humans learn these games.
well said!
like chess reaching perfect is impossible. you will never be able to compute every move in chess
"This is the most complex set of instructions ever made for preparing microwave burritos"
-Extra Credits
Yes! A video on emotional engagement with AI would be great!
What is the most annoying game AI you had to deal with?
Rad¡o Head basically any companion ai except Elizabeth
Rad¡o Head nothing specific, but when you have to lead someone from point A to point B as a quest, and the AI is so bad that that they end up walking into walls and can't get through doorways.
Probably any escort quests. Just pick one.
Dice AI
rome 2 on launch
The animation in these has been off the chain lately! As always, I'm loving your work guys!
Well you know I think some cases more life-like AI may be better. Like in skyrim where people have a schedule, some kind of disision tree swapping, or when you get 2 ai next to each other and they start talking.
Fuck, I just wrote a long comment about that, and now I find yours:D
Curtis Jones Ohh, and are you annoyed by the "I give up" npc line, they run away but start fighting again, and the fight doesn't end:D
How complex and in what will the AI be complex in is completely dependable on what genre and type of gameplay you are going for with the game, if not thought thoroughly it can destroy the gameplay
The two cases you described are not complex situations, they are referring to the kind of AI the game uses when the player interacts with NPC's, a schedule or interaction between NPC's is not always that complex (it may look like it is, but most of the time is not).
Didn't Spore (2008) have a feature in the tribal stage where two ai would talk if they were near each other?
Hey Extra credits, is there a way to get your viewers to suggest a topic for you? But not for your Extra History series.
Hi Kabloosh! Currently there is not any formal method of guaranteeing that a viewer-suggested topic will be featured on Extra Credits (the way that Extra History topics can be suggested and voted on). Most people just tweet/email/message us about their ideas anyway. We do read them all!
Extra Credits I know it is ironic to reply to this comment with a request but I have an interesting topic. How do fanbases affect games. For example Minecraft and undertale
ok, thanks for answering!
doggo mcwoof
I doubt it.
Plenty of other channels have already covered that topic TO DEATH exactly because of Minecraft and Undertale.
Zach Fischer yaaasssssss Minecraft and undertale.
6:49, your dearest artist just summed up the 'uncanny valley' in one picture, good work!
Video game AI is my dream job. I'd love to learn how to make something like AI for a monster in Monster Hunter. Love the video!
Geoffrey Perrin A? why not multiple
It's hard as fuck but go for it. Study up on mathematics (particularly calculus and algebra). Then go for discrete math and algorithms. Programming is also a must at some point. Then you can get directly into the meat of it.
I'm actually already a graduate of computer science and game design from my university, it's just that I can't make AI work my first job, i'm not prepared as most of my work hasn't required much AI, so I don't have any AI work to show on a portfolio (working to resolve that)
DemonGrenade274 I disagree. You certainly will need such knowledge for game development in general, but not for AI in particular. Like this video says, AI isn't as difficult or scary as you think. The scarier the prospect of creating that AI, the worse that AI will almost certainly be, especially for a Monster Hunter or Dark Souls style game. There will be no machine learning or neural networks here (I feel I should note that AI in games is very different from AI in education or research). You can always make an AI simpler by mimicking real choice with a decision tree and a bit of RNG for flavor, for most games no one will know the difference.
In terms of decision making, it mostly just comes down to a tree of decisions that it makes periodically. If player behind me, do tail swipe. If player in front and close, do bite. If player in front and far, breath fire. That kind of thing. If you wanted to add a bit of variety in, you simply roll an RNG and make a choice based on that. If player behind me and rolled 0, tail swipe; if player behind me and rolled 1, tail slam. Actually implementing the attacks or movements goes beyond AI itself (though it is notable "Video Game AI" is not a full job on its own, it is simply part of being a game dev :P)
Regardless, the key thing to remember is that, in general, what you really want is an AI that _appears_ to be smart. You don't want to try to actually make it smart, it will usually just end up a lot dumber for the effort. Oh, and I would be remiss not to mention Ellie from The Last of Us and Elizabeth from Bioshock Infinite as good examples of AI that can appear smart in a variety of ways, and yet are still far simpler than their choices seem. I think the Bioshock one even has a video of the devs discussing it somewhere... I'll leave you to look for it on your own though.
Geoffrey Perrin I'd love to do computer science and chemistry and zoology when I graduate ( I know it's not the year 1500 where that would be really possible even computer science) but I feel like the public doesn't see science and I can't explain it and I've been wanting to make a game where the ai re able to build and learn a kind of mid evil based game and it's kind of a experiment to see if a ai can out class a human at building a successful civilization.
+1 for an episode about emotional intelligence AI
An interesting question regarding AI: how do developers make it bad at stuff? For example, I throw my grenade at the bad guy. Sometimes, they're not quick enough to dodge away before being blown up. Or their aim is off when attacking you. What goes into deciding how often the bad guy tries and fails to accomplish what is in its decision tree?
A good question.
I guess they put in a random number generator that triggers skripts that make the NPC miss or screw up a dodge.
A term I have heard regarding shooters is: "Designing a perfect AI is easy, making it beatable and realistic is the hard part." I can why it would be the case. The perfect playing AI always hits a headshot the moment it can see the player, but that is hardly fair or fun. Delays and variables need to be a part of it.
As someone who's dipped their toe into MUGEN a time or two, I would dearly love the answer to this question.
It might have been on this channel or another similar one, but I heard that in the Uncharted games the AI is programmed to always miss you for a specific amount of time after you come out of cover.
A very interesting question. After all if the AI in a shooter game actualy worked at 100% of it's capasity then every enemy would literaly BE an aimbot.
That cover-diving enemy is weirdly charming.
James talking about Emotions in gaming is always a definite plus!
Hello! Game AI Programmer here! Just figured that I'd mention the thing about behaviour trees driving an AI isn't strictly always true. Behaviour Trees are definitely the most common one, and very powerful, but they work on a very "yes" and "no" basis, but sometimes that isn't powerful enough, for games like RTS's.
There's a bunch of ways to implemented this, like Utility Based Reasoning, to work in a much more fluid way. It makes it much less predictable, but for some games that's what you want.
Anyways, just thought I'd throw out there that Behaviour Trees aren't the be-all and end-all! Thanks for the video, have a great day to anyone reading!
I think a great example of this is Dark Souls AI. It's often predictable, intuitive and exploitable, but it's always engaging. There's just something about fighting a Dark Souls enemy that's fundamentally engaging.
Please come back to this! I work in a GAME in the UK and your show helps me to do the work I love and enriches my understanding of my favourite hobby. Please never stop.
Extremely interested in seeing how they could be used to create narrative elements.
I enjoyed the addition of the small amount of animation in the characters sneaking up on each other. Good job on that.
How does this apply to CPU players in fighting games and RTS's? I would think that in that scenario a more complicated AI is the better option so that a player can play possibly thousands of variations of the same scenario (eg. Fox only no items Final Destination) and still see new outcomes.
they never said that complex ai is bad.
They said complex ai doesn't nessisarily mean better.
In some circumstances, yes, complex ai is better.
I just considered that because I am far less engaged in a game when I have a general sense of what the AI is going to do, which is the exact opposite purpose of AI as they stated. Even when I play an FPS I'd rather not know what would happen, but instead make assumptions that could be wildly off base and improvise when that occurs.
Not necessarily complex AI but many different AIs. The worst thing for an RTS is for every faction/side to behave the same regardless of how complex that behaviour is.
Not exactly complex, but it does need a good learning pattern ai, it doesn't need to make complex decisions, but it needs to read the players movements and move accordingly, forcing the player to change the strategy used.
Stephen von Schulmann you got a point. More complexity in the cpu make the game Harder and more fun to discover. Fighting a lvl 9 fox would be very borring if you could read every reaction
I had a discussion a while ago with a friend about this. He said that games had working low-level AIs, I said that those were only decission tree's disguised to look like AIs. He told me then that those decission trees were the AIs, that all form of interaction with a world, being an ant, a human or game AI were a result of decissions, just with different levels of complexity.
Very interesting episode! I'd say there's definitely a time and place for complex AI, but sometimes it just might not be that time nor place. Also, I would definitely be interested in an episode about AI impacting the emotional experience!
emotional can be had at even really basic AI....
I had a guard in Hl1 survive a encounter against a hostile Marine and well I did what I could to escort said guard to safely (or a ladder).
((the security guard even whit there crappy pistil could still kill a marine in a 1 vs 1 if the fight was on mid range mostly becos the guard had better aim))..
the short range and the marine won all the time.
I don't even play video games all that often (MAYBE once a week for two hours) but you guys just have such engaging content that I keep watching these videos like an addict. Thanks for making RUclips better!
"When we talk about AI in games, we're not really talking about artificial intelligence. We are talking about decision trees" made me shudder. There are lots of different types of ai in games. Decision trees are not even the only type of expert system in games. One of the most common AI in games traditionally was decision trees. Nowadays there are all sorts of AI from bleeding edge neural networks, to heuristics like the A Star algorithm, to even cellular automata.
Add finite state machines to that list. That's another common approach.
I wouldn't be surprised if there are game AI systems which use more powerful models, like pushdown automata, too.
Parts of GalCiv2 AI worked like a chess computer, using the free CPU power during players turn to calculate turns ahead and choose optimal outcomes. So the longer the player took their turn/more powerful CPU would mean more better play by the AI opponents.
I remember hearing about a game that had various 'traits' for their enemy ai. Basically, performing or observing certain actions could raise or lower variables such as 'courage', 'morale', and 'stress'.
Higher courage would allow the ai to stay out of cover longer and get closer to damage sources.
Lower morale would make the ai more likely to hide or avoid engaging you, and make them less likely to attempt to achieve objectives.
Since the ai could adapt on the fly, it made gameplay very interesting, as you could use intimidation tactics to scare the enemy away, and the bots would constantly try to counter your tactics, requiring you to switch tactics often.
Unfortunately, I don't remember the name of the game, but it was great fun the one time I played it.
well fuck now i gotta go have a microwaved burrito
This video's release is quite terrifying since I've been working on Game AI all day.
I am quite interested in AI influencing emotional experience, so please do the episode about it!
Would love to see an emotional/narrative A.I video
As a player, 3 examples I can think of that I have seen are:
-When game music changes depending on the player state, environment, etc
-A.I speech. "SQUAD NEUTRALIZE FREEMAN"
-When you pull out a weapon and NPC's run or change behavior (e.g in STALKER, NPC's tell you to lower your weapon before you can speak to them)
Here I was just beginning to make an ai for my game and EC just so happens to come out with this video.
Coincidence?
I think so.
So what AI technics have you discovered?
8:05 "How does this [behaviour I am about to add] set up an opportunity for the player to make interesting decisions within the game?"
Brilliant. Thank you.
*Immediately thinks of Dark Souls enemies*
I have to recognize that this particular video (and surely many more) have a really good time management, I truly felt like there was a good amount of information in a short window of time which was easy to grasp and understand. Also, I was thinking around the 4-5 minute mark that the video was about to end but there was still more left (which that is really awesome). Congrats on the good writing/directing of the video and keep at it with the good job!
What a fascinating topic!
This even applies to AI filling in for human players in games like Civ. One of the enjoyable thing about competing with humans is that they have complex plans but that the plans do have logic to them and if you can figure them out you can outplay them.
But how many times it actually is the case of over-engineered AI vs not enough attention paid to good AI? Most of the time AI is just god damn awful. How many times your teammates get in the way? How many times in RTS the opposing AI simply cheats instead of playing better? Etc, etc. I don't think developers need incentive not to invest in AI, as they do a fine job of it now..
Vaidas Šukaukas I think that in order for an AI to appear smart you don't really need a lot of decision paths, just don't make them DUMB. Like you said, team mates standing in the way, or in Crysis (I am playing it right now so it's a pretty specific example that I could remember) when you shoot enemies with a silencer they will just stand there instead of looking for cover
Input on the emotional interaction between player and AI would be fantastic. I've just launched my game dev crew and I'd like to give my team the chance to really focus on that aspect of a game.
Yeah, I personally want to come back to the narrative part of AI.
Seriously I feel like I'm the only one here who doesn't work or plan on working on a game, these are just good videos that I like and they shed light on the gaming industries as unbiased as possible, good on you James and crew
Paradox please see this
Johannes Berger lol
@@yoavmor9002 lol
oh man PLEASE come back to this. This episode was super informative and interesting but I was a little disappointed it was only about Enemy AI. hopefully this latter portion they teased is where non-enemy AI comes in. can't wait!
I am very interested in emotional engagement via AI.
I'd love to see an episode on how AI can emotionally engage the player!
The closest examples I can think of that is when Sif from Dark Souls starts limping and attacking slower when his health is low, or how the Fume Knight from Dark Souls 2 will go into his second phase immediately if you're wearing Velstadt's helm. Those are narratively driven events and change the fights quite a bit.
But I can't think of much else.
I have a suggestion for a video. Over saturation of the video game market
nah
The art for these videos are getting better by the episode, good job!
For the topic you said for the end of your video Look to The Last Guardian!
I'm most definitely interested in hearing about the emotional and narrative utilization of game AI - as someone who wants to get into game development in the near future and create narrative-focused games, learning about any tools I could possibly use would be fantastic.
Pitch this video to Bethesda.
It's a joy learning from this channel
There is one thing I have to disagree with you, EC.
A.I. should't be intuitive. When an A.I. is stripped of its masks and made naked by the player's eye, the singleplayer experience is dead.
I bring RTS A.I. as an example of this; not the units but the enemy CPU.
But it is also true with FPS, (I exploited quake2 A.I. on multiple occasions) and I bet with many more.
I see the point you are trying to make here - behaviour should be more natural and unpredictable. Yet all games from Halo to Splinter cell are all about devising a plan and then putting it to action. If you throw that grenade and the enemy runs for cover only 50% of the time then you don't get that satisfaction of being a strategic thinker. Same with guys in stealth games always annoyingly voicing their thoughts.
I see many ways AI could improve while not becoming more unintuitive, reacting more diversely to more player actions is one of them. They see you carrying a shotgun - they will try to keep their distance, you broke into their compounds unseen armed with a tranquilizer gun - they will set up traps, you walked into the women's restroom - they will berate you for being a pervert. It's not in unpredictability, it's in variety, because games are solid mechanics to be conquered with diverse skills.
There is no one definitive answer. The Mario games would not benefit from unintuitive AI, in fact, they would get worse by making the AI less predictable.
Well, that´s why he said over time. If you can´t learn an AI, then it´s no better than an random number generator, because unpredictable decission mean it rarely does the best decissions. It also wouldn´t make the NPCs more lifelike, but less. In real life you learn to predict people, too. That what makes you connect with them. Someone who is completely unpredictable isn´t a good character but a psychopath. It would get even worse if those were mission critical and on your side. Remember every escort mission you ever had with a bad companion AI. Now imagine those missions with completely unpredictable companions.
That's a flawed concept for FPS's if you've actually been in any kind of fight. Plans never survive first contact, and enemies being predictable is absolutely immersion-breaking.
An AI can be unpredictable and still have reasonable decisions. It's no the same as making random decisions.
Meanwhile rain world not caring and proceeding to make best AI in games while completely ignoring this video.
This is one of the reasons why games like monster hunter got under my skin. Besides the various tells the monster gives you before using an attack, there was no way to know which attack it'll do next. It makes the hunts exciting and different, but it also makes me want to murder someone with a spoon whenever it initiates an attack that is completely inescapable for me.
In fairness I think attacks like that play a big part in the "makeing interesting problems for the player" part of an AI's job in a game.
While it would be frustrating to die or get screwed over by that inescapable attack the first time, on every subsequent encounter with that enemy you know they have that ability.
At that point the game shifts gear from "spot the tell and react" to "figure out how to bait the AI into doing it's less anoying attacks".
Heck as a SoulsBorne veteran I can say that for my own part knowing how to bait the attacks I personaly find easiest to deal with is 80% of how I beat most bosses (and even most reasonably hard enemies) in such games.
theyre only inescapable because you put yourself in the wrong position at the wrong time. one of the things i love about MH is that every single attack is completely avoidable, and its completely fair that i got smacked by it. they are hard games. very hard. but theyre just too fair.
justdontask3
While I agree, to be fair the AI is also a lot less predictable than in older games both in who they target and in choosing attacks.
I think most of us run into those situations where they home in on one player or spam or chain attacks at some point.
For me that was Deviljho, it followed me around a few minutes spamming its head-swipe, with the occasional boulder or body-check.
I survived several close calls while the other guys sat and watched.XD
I have no idea why I enjoy these videos, but I genuinely do. My thanks to you for creating your content, even if I can't put my finger on why I enjoy it!
Hmm what games have the extra credit crew worked on?
James has been a part of Rainmaker Games, Snow Cannon Games and was the CEO of Divide By Zero games.
I don't know about the rest of the crew.
Please do more episodes on AI. Especially real AI and how it could work with games.
3:54
Like Halo?
You guys could pitch literally any episode idea on any facet of game design and I would be hyped to learn more. I love learning how things fit together, and I love games, so even though I'm nowhere near a career in game design, It's still fascinating to learn how games are put together and then recognize those facets in the games I play.
TL;DR, I'd love for y'all to do an episode on how NPC decision trees can augment the Narrative of a game, and I'll even toss the first idea of an example. In Halo, the enemy Hunters always travel in pairs, and when you kill one hunter, the second one goes berzerk and charges you to initiate a smashfest on your face. Even if you don't know exactly why they go into fury mode (It isn't what most people might think) It's easy enough to intuit that this hunter is angry over loosing it's partner. Small touches like that can add massive levels of depth and immersion to a narrative, all without a single cut scene or word of dialogue.
AI, Artificial Idiots. That being said once you have fought a learning machine, humans don't offer a meaningful challenge anymore.
Please come back to this. I want to know how an NPC AI can make me cry
In Soviet Russia, AI Programs YOU.
This goes back to your video on "Depth Versus Complexity". I would love to see more videos on game AI. Sometimes the environment is a complex AI as a whole, but is distributed through simple entities or attributes that fundamentally resonates in a granular snowball like fashion, intuitively resonating with and affecting the player in nuanced ways.
*warmonger*
As I a soeedrunning I can say that learning how AI reacts to situations is very important for getting the game done fast and thus being enter at it, all of this is true.
Video is good
However - can you stop using the word SHMUP
Why
ikr? it irritates me for some reason and i don't know why.
This episode has been especially helpful for me as i am currently pondering on how to improve my AI for a squad tactics game im working on as a hobby project. Thanks for the help, and I'd love to see you talk more about AI!
I really like the AI companions in Star Wars: Republic Commando. Not only are they decent in combat, and very distinct in what they do, but they are also interesting with their side commentary. It makes you really enjoy them as squad mates and makes you take that extra step towards trying to get through each level together. That is good AI programing.
Your content is gold. Animations make this flawless.
One thing I'd like to see used more frequently is the idea of an "AI director" overseeing the NPCs' behavior, so they're not just all autonomous units that could interfere with each other or accidentally gang up on the player in ways that are impossible to counter. Games where enemies infinitely respawn would especially benefit from systems like that.
I think James is deeply interested in almost EVERYTHING. Good on him. Means more cool stuff for me.
metal gear solid 5 had NPC AI that drove my emotions. after getting spotted and trying to fight my way out of a situation I became overwhelmed and had to take cover. as i waited for everyone to stop searching for me, I was shocked to see the surviving NPCs go to each of their fallen comrades and grieve over them. suddenly, for a few seconds, these weren't just video game bad guys, they were real. it made me rethink my plan to attack when their guard was down and instead be especially careful to just sneak out undetected. this might be a good example to use when you do that video on AI driving emotional responses.
INTERESTED IN MORE ABOUT HOW AI CAN FACILITATE NARRATIVE ENGAGEMENT.
THANK YOU, KEEP UP THE GREAT WORK.
Yes, yes, yes, come back to this, pleeeease! I love this topic!
Gotta admit that, even though so many of my fav games fill into interesting AI behaviors that are simple, some of my fav experiences on non demon/alien/robot combat in games haven't been rivaled for over a decade. And that is Half Life's soldiers and FEAR's troops. The way they communicate between eachother and how elaborate (in relation to most NPCs even to this day) to how you place yourself in the map, the way you move, the way they move, your attacks and theirs, how they coordinate, haven't had as exciting firefights on any game that isn't highly exagerated on fantastical on enemy variety and attacks (which is most modern shooters) since then.
PS: I freaking love the FPS Behavior char design you guys did! It's so damn adorable and I was glad you didn't show him getting killed, cause gotta admit I'd have felt sad x3
Do come back to the part about affective computing, it's an interesting area that deserves lots of attention.
Just want to say. This is one of my favorite EC vids in a while, as always fantastic job guys 👍
technically speaking visual novels use decision trees for emotional interaction, it just feels less organic because the player is using those same decision trees (and when it's a bit more sophisticated, like a chatbot, immersion is usually tough not always shattered)
I was going to make a comment saying "Yeah, then how does this work with your points made in your "Strategic Uncertainty" video eh?"
5 Minutes in that video, you addressed it. Kudos, very consistent haha.
I just got a B in I.C.T for my end of year exam
We had design a simple AI and this vid really helped
thx
4:25 Mr Game and Watch! Your visual aids keep getting better and better! 😄
The use of AI to promote narrative engagement does sound very interesting! I'd love to hear more about that!
The art was great in this one! So many fun little visual gags.
For your last question... the one where you ask "how to use A.I. to increase emotional/narative engagement", I think you can find the answer (or part of it) in Mark Brown's Game Maker's Toolkit episode about "The Last Guardian". He had a happy accident while playing the game that shows how such an A.I. can work.
5:00 there is a videogame called Gladiabots where you make decision trees for gladiator bots. Check it out
The art is just getting better and better
I would incredibly enjoy James squeeing about emotionally intelligent AI to increase story impact.
The question of emotional engagement is quite interesting, and I would like seeing an episode on it, as you suggested.
This was one of my favorite episodes in a while I think it would be awesome if you talked more about this topic or others like it
Awesome. I'm working on an AI series myself, so this was very helpful. Please do continue making more AI related videos, it's such an interesting field.
This is the first video I watched from your channel. I later discovered Extra history and the rest is history
heck yes come back to this. Would love to hear more about this.
"AI to increase narrative or emotional engagement" sounds like a excellent video idea!