Reinforcement Learning: Crash Course AI #9

Поделиться
HTML-код
  • Опубликовано: 2 ноя 2024

Комментарии • 76

  • @jimmybutler4076
    @jimmybutler4076 5 лет назад +77

    Yo as a black guy with dreadlocks who likes coding, it’s really cool to listen to another black guy with dreadlocks who likes coding

  • @hjaiswal768
    @hjaiswal768 5 лет назад +110

    "A trade off between exploration and exploitation" - Thats life

    • @peka2478
      @peka2478 4 года назад +2

      Well, no,
      (Conquistador) Life can be both.
      Usually is.

  • @shashanksams
    @shashanksams 5 лет назад +15

    yay, this was actually better than most of the explanatory videos i have seen. thanks for providing us always with informative content, crash course. looking forward for more of these videos

  • @TheCheck999
    @TheCheck999 5 лет назад +39

    8:38 John Green bot from the past

    • @cesardachimp8172
      @cesardachimp8172 5 лет назад

      oh man, i didnt notice that

    • @Pravaification
      @Pravaification 5 лет назад +5

      *waves robo hand* Mr. Green Bot! Mr. Green Bot! What if I took TEN actions?

  • @cesardachimp8172
    @cesardachimp8172 5 лет назад +76

    Can we do Crash Course Law?
    Like if you agree

    • @masternobody1896
      @masternobody1896 5 лет назад +1

      Crash course doesn't make sense it makes jibril look bad

    • @nealkelly9757
      @nealkelly9757 5 лет назад +1

      How about crash course Current Events. It's so hard to keep up with all the developments in US politics and such

    • @Muhammad_Syakir
      @Muhammad_Syakir 5 лет назад

      PBS can try invite Meghan Markle and her team to do all the law educational stuff, she is very good at it. :)

    • @thethirdjegs
      @thethirdjegs 5 лет назад

      @@nealkelly9757 crash course current events would have indefinite number of episodes.

    • @cesardachimp8172
      @cesardachimp8172 5 лет назад

      @@masternobody1896 ??? what do you mean?

  • @thebrianpaige
    @thebrianpaige 5 лет назад +24

    Loving this series. Thank you so much! There's so much info in every episode; just fantastic.

  • @janyjj1969
    @janyjj1969 5 лет назад +4

    I WOULD LOVEEEE IT IF CRASH COURSE HAD AN ACCOUNTING COURSE!!❤️️.

    • @Logan_Explores
      @Logan_Explores 5 лет назад +2

      Jany JJ try Kahn Academy. I’m pretty sure they have an accounting section.

    • @janyjj1969
      @janyjj1969 5 лет назад

      @@Logan_Explores Alright, thank you so much😻.

    • @randomalpaca
      @randomalpaca 4 года назад +1

      US or Canada or other?

  • @krellend20
    @krellend20 5 лет назад +8

    Jabril really has it out for bagels.

  • @NStillman
    @NStillman 4 месяца назад

    This is the best explanation I have seen so far - definitely sharing - thank you!

  • @gitoshrisen7687
    @gitoshrisen7687 5 лет назад +4

    This reminds me of Pavlov from my psychology class.

  • @StevieRZ
    @StevieRZ 5 лет назад +4

    now,after watching multiple episodes in a row, I really want donuts :P also really enjoying this series :)

  • @pedro_a_martins
    @pedro_a_martins 5 лет назад +5

    I'm really liking this series of videos
    Keep ip the good work :)

  • @shendosmani4509
    @shendosmani4509 5 лет назад +4

    5:12 open all no risk high reward

  • @_Baleful
    @_Baleful 2 года назад +1

    This video is fire. Insta-subbed!

  • @MarkyMark1221
    @MarkyMark1221 5 лет назад +10

    Can we get crash course geography

  • @jacquelyncuturic8072
    @jacquelyncuturic8072 Год назад +4

    jabril got a new hat did u notice?

  • @LearnandGrowKidsTV
    @LearnandGrowKidsTV 5 лет назад +3

    Such a great video!
    We most definitely do whatever it takes to get more cookies 🍪 😉

  • @pinkponyofprey1965
    @pinkponyofprey1965 5 лет назад +9

    0:17 That cookie looked completely ... edible hahaha! What brand is that? :D
    Screw Reinforcement Learning .... I'm now officially hungry!
    [back from the kitchen]
    Reinforcement Learning is actually extremely interesting! :D

  • @itdepends5906
    @itdepends5906 4 месяца назад

    Nicely explained, thanks

  • @rajcivils
    @rajcivils 5 лет назад +3

    Are you going to use openai for rl and keras when we come to deep reinforcement learning
    When will this playlist be finished.

  • @cornellwaters9089
    @cornellwaters9089 4 года назад +1

    🏃 Thank You!

  • @chaneldelarosa9786
    @chaneldelarosa9786 4 года назад +1

    Thank you!

  • @TheBlizzardfan7
    @TheBlizzardfan7 5 лет назад +2

    Thanks for your Awsome Course, I got interested in Machine learning and I am planning to study that for my M.A.

  • @nahhale9088
    @nahhale9088 5 лет назад +6

    Can we get crash course music theory?

    • @lincolnpepper816
      @lincolnpepper816 5 лет назад +1

      that's the main thing i've been wanting for years and many people have asked for it. So you know, i remember on one other comment asking for it crash course replied that they've been thinking about it as well. Not sure what the chances are now, but that gives me hope

  • @billniko9310
    @billniko9310 5 лет назад +1

    Can we get computation theory lesson ,CC ?

  • @geoffreywinn4031
    @geoffreywinn4031 5 лет назад +1

    Cool video!

  • @kurtphilly
    @kurtphilly 5 лет назад +3

    I don't agree with the bagel/donut choice example. Why choose the option of two bagels or donuts vs. the greater risk of more donuts (6) or a guaranteed single donut?

  • @TreeNap
    @TreeNap 4 года назад +1

    In the john green bot example, is the objective to find the shortest path or get the most points? What would getting more points even do, I feel like in that case exploration is best so that you can find the shortest path, exploiting only when racing another bot

  • @void2509
    @void2509 4 года назад +2

    5:11 I'll just take all three items

  • @johnopalko5223
    @johnopalko5223 5 лет назад +1

    This fellow and his donut obsession. I don't know... 😊

  • @dvklaveren
    @dvklaveren 5 лет назад +1

    Black & White and Black & White: Creature Island used reinforcement learning. The creature you commanded could learn incredibly complex routines, such as planting a sapling, water the tree with the water miracle, then pick it up and throw it into the resource center and repeat. With enough training.
    I really hope that we'll see more games exploring that kind of relationship with a computer character. Imagine a game where you're personally teaching a group of monsters how to hunt and then guiding their instincts by reinforcing or punishing a particular set of circumstances, until they conquer their world.

  • @sarujanrupan4831
    @sarujanrupan4831 5 лет назад

    It's Jabril!!!

  • @ianrbuck
    @ianrbuck 5 лет назад

    Not sure the kitchen metaphor works for me. Why is the bag more likely to contain donuts than the box? It sure looked like the kind of box that donuts come in to me.

  • @anttibjorklund1869
    @anttibjorklund1869 5 лет назад +1

    Why would JohnGreenBot in that battery example only go in straight lines? Would it not be better to go in a diagonal path?

    • @EclecticFruit
      @EclecticFruit 5 лет назад +1

      because that is how he was taught to see the room and navigate it. If you want diagonals, maybe we'd have to arrange the room in hexagons instead.

  • @billniko9310
    @billniko9310 5 лет назад

    Love you love you love you love ❤️

  • @dkecskes2199
    @dkecskes2199 5 лет назад +2

    9:40 is my hometown. Ok AI, good reinforcement for me.

    • @slikh
      @slikh 5 лет назад

      Yeah, I recognized Boston St too :)

  • @castro_hassler
    @castro_hassler 5 лет назад

    Nice ,

  • @Graghma
    @Graghma 5 лет назад +1

    Is there a better reason than consolidating the total amount of stored data the reason we only store a single value per square? Why not store 4 values per square so you can store a value per direction you could go from the current spot. That way you could find/exploit the near black hole shortcut that the current algorithm is too scared to find.

  • @alexixeno4223
    @alexixeno4223 5 лет назад

    I feel there are people in place of power/rich who need to watch this video... >.>

    • @JustaReadingguy
      @JustaReadingguy 5 лет назад +1

      Outline what they should take way from the video and why.

  • @TheSentinelAI
    @TheSentinelAI 5 лет назад +1

    🤘🤘🤘

  • @amitzahirr
    @amitzahirr 4 года назад

    is this related to dijkstra's or a*?

  • @user-zu6ts5fb6g
    @user-zu6ts5fb6g 5 лет назад +5

    When jabrils is talking his mouth is moving. That is illegal.

  • @AB-vw8wz
    @AB-vw8wz 5 лет назад +1

    Markov decision process and Q learning, fcking tedious

  • @senthu07
    @senthu07 5 лет назад

    12th comment is mine...

  • @COOPSTOP
    @COOPSTOP 5 лет назад

    Agent? like..... Agent Smith???!!!

  • @hamzadbz1
    @hamzadbz1 4 года назад +1

    Who drives a car looking at side ways?

  • @Maicha943
    @Maicha943 4 года назад

    Open Ai and Alpha Go

  • @jimmyshrimbe9361
    @jimmyshrimbe9361 5 лет назад

    That was a robot playing Don't Wake Daddy.

  • @rintume8631
    @rintume8631 5 лет назад

    Like if AI beats slavery

  • @masternobody1896
    @masternobody1896 5 лет назад +1

    Knowledge but man I don't understand can you make it easy

    • @thethirdjegs
      @thethirdjegs 5 лет назад

      This episode is hard because it's oversimplified

  • @fabio2234
    @fabio2234 5 лет назад +1

    First second!

  • @clvrswine
    @clvrswine 5 лет назад

    Jabril? Jabril? Laughing too much to type. Hey, I'm Jabril. Unreal, these people.

  • @sefp
    @sefp 5 лет назад

    Rare too see a black guy talking about this subject but glad I did.

  • @liliabel3160
    @liliabel3160 5 лет назад

    You're good but You are going too fast