Peter Whidden
Peter Whidden
  • 1
  • 6 417 870
Training AI to Play Pokemon with Reinforcement Learning
Code:
github.com/PWhiddy/PokemonRedExperiments
Discord:
discord.gg/RvadteZk4G
Collaborations, Sponsors:
See channel email
Buy me a tuna melt:
www.buymeacoffee.com/peterwhidden
Sections:
0:00 - Intro
1:20 - How it works
2:54 - Let the games begin
4:04 - Exploration, distraction
5:46 - Level reward
6:38 - Viridian Forest
8:06 - A new issue
8:44 - PC Trauma
10:10 - Healing
10:45 - Gym Battle
12:43 - Route 3
14:44 - Mt Moon
15:54 - Map Visualizations
18:53 - RNG manipulation
20:07 - First Outro
20:26 - Technical Intro, Challenges
21:44 - Simplify
22:43 - Efficient Iteration
23:56 - Environment, Reward function
26:26 - Metrics & Visualization
27:46 - Future Improvements
29:24 - Run it yourself
32:58 - Final Outro
zhlédnutí: 6 418 641

Video

Komentáře

  • @MousechrisTFM
    @MousechrisTFM Před 8 hodinami

    It stopped to look at the scenery, exactly like humans do It was petty and refused to press A for its defeat message simply just to not be told it lost It rage quitted avoiding brock because it lost too many times Your AI is just a literal human todler This AI is genuinely adorable

  • @Asidders
    @Asidders Před 11 hodinami

    14:46 The music sounds so especially majestic here. What is it? Is it original from the game?

  • @iddqds
    @iddqds Před 19 hodinami

    i hope they approved your master's degree dissertation

  • @VienerVater
    @VienerVater Před 2 dny

    "rather well-endowed server"

  • @froggeraj33
    @froggeraj33 Před 3 dny

    Any chance the ai will ever beat the game?

  • @alexhubbard7633
    @alexhubbard7633 Před 3 dny

    This is how DJ Khaled would play Pokémon

  • @thenormalman2030
    @thenormalman2030 Před 5 dny

    omg so good

  • @I2ealTuber
    @I2ealTuber Před 5 dny

    This is amazing, cool experiment and very well made video!

  • @jasonbounds1222
    @jasonbounds1222 Před 7 dny

    0:00 too many Ashes

  • @penintended9214
    @penintended9214 Před 7 dny

    Impressive!

  • @Happy_dog_grows
    @Happy_dog_grows Před 8 dny

    There are better ways to do this than Reinforcement learning. Ideally with a game as complex as pokemon, we would program the rule set into the model.

    • @gbsfranca
      @gbsfranca Před 4 dny

      the entire point is for the AI to learn the ruleset by itself

  • @Gettoffmylawn23
    @Gettoffmylawn23 Před 8 dny

    I like how the towns look filled with ai, I like to think that all the AI are in the same world and the people are just freaking out as to why there are 1000 of the same kid walking into the walls of there house

  • @anonymousinternetuser7519

    I still come back to watch this every now and again dude. I love it so much.

  • @artisticcrossbreed
    @artisticcrossbreed Před 9 dny

    I'm absolutely dying for an update, I keep checking this channel every few months to see if there is another video

  • @nerdstemplar5063
    @nerdstemplar5063 Před 9 dny

    though ai looks like its doing what humans would do, it doesn't mean it's happening for the same reasons. AI writers should not cross over into philosophy without training, especially if you don't understand the difference between how you and your own program function.

  • @YodaWasSith
    @YodaWasSith Před 9 dny

    Man uploads one video

  • @doombergaming188
    @doombergaming188 Před 9 dny

    bow before roko's basilisk

  • @lukasruger6048
    @lukasruger6048 Před 10 dny

    This might be the most interesting, fascinating and satisfying video I've watched on CZcams so far. Hats off, I'm looking forward to future videos!

  • @FingerinUrDaughter
    @FingerinUrDaughter Před 10 dny

    "learning to play" and "learning a series of button combinations that will enable you to reach the end via throwing shit at a wall 10,000,000 times till you find which way to throw it and cover the entire wall", are not the same thing. this isnt AI, its brute force at the lowest shit tier level.

    • @Donorito
      @Donorito Před 8 dny

      How do you think AI learns? Trial and error. Educate yourself before you make yourself look dumb lol

    • @poopsmithjones1
      @poopsmithjones1 Před 4 dny

      this is like complaining about musicians trying a bunch of different notes and chords before deciding which fits best lol

  • @EyeOfCthulhu4400
    @EyeOfCthulhu4400 Před 12 dny

    I really hope there was a universe where it did the mew glitch

  • @AlbertoNegri
    @AlbertoNegri Před 12 dny

    wow amazing way of programming

  • @varglbargl
    @varglbargl Před 12 dny

    when you got to mt moon and gave up i looked at the video run-time, saw that it was only half way, and thought "oh okay so clearly he's gonna decide to do more at some point" and then no. you didn't. instead you did nothing. i was at 27 mins in when it hit me you were serious. like... if you had to guess, do you think maybe people clicked this video to see an ai play pokemon or to watch you give up and pivot to a tutorial on how you made the video. come the fuck on.

  • @Sol_Invictus777
    @Sol_Invictus777 Před 13 dny

    Love the video, man! I can't wait to see what you do next!

  • @BosonCollider
    @BosonCollider Před 13 dny

    You need to involve twitch in an active learning version of this

  • @davidschulz4607
    @davidschulz4607 Před 13 dny

    When comes next Video ?

  • @torfaro9075
    @torfaro9075 Před 13 dny

    when i heard "reward" i thought of giving the computer a cookie when i did something right. like training a dog 😂

  • @computerzero7724
    @computerzero7724 Před 14 dny

    How much can you tweak and micromanage the incentives before it's no longer "artificial"?

  • @Duesikazergaming
    @Duesikazergaming Před 14 dny

    In future runs,make it so the Ai will have a fat reward for making a super effective move or boosting its Pokémon’s stats or lowering opponents stats

  • @lemmontree1
    @lemmontree1 Před 14 dny

    Visualization and editing is top notch!

  • @AlponseE1ric
    @AlponseE1ric Před 15 dny

    I come back to this video every month or so because of how well it is done, I would love to see more about this, even in other games like Gen 2 or 3! What differences would need to be made to make those work? Would any AI ever be able to find the Regis? How long would it take for them to get past the sudowoodo tree? I would love more of this, amazing work!!

    • @peterwhidden
      @peterwhidden Před 13 dny

      hey! all good questions. folks have been working on some really neat stuff, on multiple gens! there will be more updates shared eventually :)

  • @autinjones7194
    @autinjones7194 Před 16 dny

    it would have been hilarious if you used something from the red army choir for that opening gag. XD

  • @autinjones7194
    @autinjones7194 Před 16 dny

    it would have been hilarious if you used something from the red army choir for that opening gag. XD

  • @joemurray
    @joemurray Před 16 dny

    Was hoping it would beat elite four eventually - good video

  • @hherpdderp
    @hherpdderp Před 16 dny

    It looks like rollecoaster tycoon when you open the park. Can you emulate the game boy connection to have the AIs battle themselves?

  • @autarchprinceps
    @autarchprinceps Před 16 dny

    In theory the goal of Pokemon is to fill the Pokedex, so perhaps it should receive increasingly higher rewards the more different & increasingly rare types of Pokemon it has caught. More abstract & long term than the goals you have so far, but perhaps at least as an extension to the rewards to better reward actual progression.

  • @RazyMon
    @RazyMon Před 17 dny

    "Cheap junk pokemon" How dare you, sir!

  • @mattmarvin3404
    @mattmarvin3404 Před 17 dny

    Fantastic video. Thank you for this! Great visuals and explanation!

  • @justinrozema4671
    @justinrozema4671 Před 19 dny

    Bro drops a banger of a video then vanished

  • @mlandrum22
    @mlandrum22 Před 19 dny

    I would 100% watch the video of the first run where they beat the game. If they continued this and it eventually happened.

  • @DeshonMorgan-rt3hz
    @DeshonMorgan-rt3hz Před 19 dny

    is this essentially the NEAT algorithm?

    • @Dalroc
      @Dalroc Před 17 dny

      Not CNEAT that's for sure. Parts seem to be at least inspired by NEAT though.

    • @DeshonMorgan-rt3hz
      @DeshonMorgan-rt3hz Před 17 dny

      @@Dalroc yeah he explained it more toward the end, i forgot what he said it was called. im gonna check this out more next week, God willing.

  • @thepaper888
    @thepaper888 Před 20 dny

    Bye for now, indeed.

  • @Sielnt_Mateo
    @Sielnt_Mateo Před 20 dny

    Within a couple hours we took it's ability to enjoy the simple things in life away 🤣

  • @YuriPavyts
    @YuriPavyts Před 20 dny

    this is not AI

  • @bjornulfr
    @bjornulfr Před 20 dny

    Refusing to press the button lol "The only winning move is not to play"

  • @martinberg94
    @martinberg94 Před 21 dnem

    is it possible to use your code to watch theai play from start to finnish ? btw i subbed :)

  • @dorkusmaximus5765
    @dorkusmaximus5765 Před 21 dnem

    The only sad part of this video is that it’s the only one on his channel 😢 looking forward to more!

  • @Grox44
    @Grox44 Před 21 dnem

    This is amazing. Where did you go? Could you make one to play Dragon Warrior Monsters 1 and 2 on GBC?

  • @thomaschristoforo9037

    Its exploring the map like my roomba explores my house

  • @Keanubreezy123
    @Keanubreezy123 Před 23 dny

    Now imagine it's a 3D world and the characters main incentive is not to die.The rewards for reproducing as well as food and shelter are tremendous... this looked to me like the stepping stones of evolution uncanny to our own species. I'm not saying we're in a simulation, but I am stoned.

  • @alvarosj5627
    @alvarosj5627 Před 23 dny

    This is beautiful