![Chrispresso](/img/default-banner.jpg)
- Видео 5
- Просмотров 483 466
Chrispresso
США
Добавлен 4 июн 2019
AI Learns GridWorld Using Pixels| Double DQN + Experience Replay
This is an AI I created based off DeepMind's paper. It uses double DQN networks with experience replay to learn to play GridWorld from just the pixels on screen.
Code: github.com/Chrispresso/GridWorld
Twitter (soon): ChrispressoYT
I wanted to start using Unity to make games so this was a good intro to that for me. The AI portion is entirely in Python which made it so I could use the Unity ML API to interface with the Unity game I created.
Code: github.com/Chrispresso/GridWorld
Twitter (soon): ChrispressoYT
I wanted to start using Unity to make games so this was a good intro to that for me. The AI portion is entirely in Python which made it so I could use the Unity ML API to interface with the Unity game I created.
Просмотров: 8 178
Видео
AI Learns to Play Super Mario Bros!
Просмотров 336 тыс.3 года назад
Using a Genetic Algorithm and Neural Network, a population of AI were able to learn to play different levels of Super Mario Bros for the NES. Code: github.com/Chrispresso/SuperMarioBros-AI Blog: chrispresso.github.io/AI_Learns_To_Play_SMB_Using_GA_And_NN Music: soundcloud.com/ashamaluevmusic first song: Memory second song: Cinematic Orchestral third song: My World
AI Learns to be a Car using a Genetic Algorithm
Просмотров 23 тыс.4 года назад
If you want to play around with the code or application, github: github.com/Chrispresso/PyGenoCar I tried to make it as friendly as possible for editing the Genetic Algorithm settings. Have a look through the README.md for setup and running. Loosely based on: boxcar2d.com/index.html
AI Learns to play Snake!
Просмотров 110 тыс.4 года назад
Using a Genetic Algorithm and Neural Network, a population of snakes are able to gradually learn to play the game with no prior knowledge! Link to code: github.com/Chrispresso/SnakeAI Music: soundcloud.com/ashamaluevmusic
Did you use a policy network?
In the video it said you trained about 5 years in 3 weeks... What hardware or cloud did you use for training? Would you recommend said hardware? How does training time compare to get to a similar level using other algorithms?
TAS VS AI
How can I display the changes in each generation in the neural network like this
Today i learned that SkyNet got it's start by playing Super Mario Brothers. Now, all it has to do is remove the human race and nobody can get more points than it does.
Hi, whereas this AI applied to games, what about another interesting aspect of AI application, making AI trade binary options, obviously on demo accounts and to see what best or winning strategy the AI will adopt to maximise its wins. Whereas most of the games require keyboard inputs, so are the trading of BO, they require Keyboard inputs, it will be interesting to see what AI does.
This voice and mannerism remind me of another gamedev youtuber haha
I so want to do this with python. And records human button plays…
Wonderful! Hope I can do things like these but using SNN
The ending was emotional
Jesus, that is some awful music.
Can I use Deep Q Learning instead of the Genetic Algorithm?
Bro ai did not get mushroom in world 1-1
Your AI could finish watching One Piece
As the narrator is speaking at 9:03 the AI walljumps again on 3-1 to avoid death in the water.
4:52 there id be...racking up 99 lives...
can you please any other video of the setup of this mario code. I need it urgently🥲
8:05 nes futurologists bot proof tech
I like how AI actually tries to speedrun the game instead of learning it
I feel so stupid, my whole life I did not know you could jump on a wall like that, and this AI figured it out on the second world. Bruh.
Ive imported the files and everthing how do i run it and what do i do (im new to coding)
Wonder if it could ever figure out level 8-4.
The irony of all these Mari/o style 'AI's is that the creators don't seem to grasp even the basics of the problem space. 99% of the 'learning' that goes into these genetic algo AIs has nothing to do with the genetic algo, the human has already done the 'intelligent' work by compressing all the dynamics of the problem space presented by the game, using human intelligence, into a simplified interpretable input state.
Very good. Did you try dropout to help reduce Mario's mistakes?
hello, your blog is 404
3:31 spring: am i a joke to you
6:15 wasn't that unnecesary?
4:37 was the wall jump
Hi, great job! I have a question: how did you come up to this fitness function?
8:30 Looks like its starting to play Snake as if it was a printer lol. Especially 3D one :P
do you write the programs from scratch or do you use a ai gym?
It follows the simple and obvious Hamiltonian pattern which guarantees not running over the tail and being able to run through every node but it’s really inefficient. I was hoping to see something smarter. Perhaps more middle layers and more generations would make it smarter. Choosing the inputs and output and the encoding can be crucial to the smartness you get out of it.
bro keep making these videos....they are very helpful...
beautiful. But the algorithm which snakes learnt is not the most efficient.
Thank you. The great one. Some questions: (1) Is there any reasoning behind the NN architecture (number of layers, number of neurons in the layer) choice? (2) What if we change all directions from absolute (U,D,LR) to relative to current head direction; wouldn't it help? (3) Why do you need crossovers; you anyway do mutation, what's the difference either to mutate the best or mix of two best?
how are you able to show the matrices on the left side screen and map performace of whats mario doing.
/
Can you make a tutorial for beginners on how yo set this up?? 😮
It was beautiful to watch! Well done
Great! but can it learn majoras mask?
please speak IA play chess
Mario is real to me 😭 you monster
odd to make a video that is basically the same as another video made 5 years prior. no way you wouldn't know about it. *MarI/O - Machine Learning for Video Games*
@Chrispresso, you're one of the best! Those who can program artificial intelligence, machine learning, and neural networks I consider to be geniuses! ;)
@Chrispresso, you're one of the best! Those who can program artificial intelligence, machine learning, and neural networks I consider to be geniuses! ;)
I wonder what is the "thinking" part in a NN?
AMAZING 👍👍
Can you make a tutorial?
Hey this is pretty cool. How did you transfer the onscreen gameplay onto the 16x16 grid show on the left side in your video?
8-1 we feel you ai!