Training AI to Play Pokemon with Reinforcement Learning

  Переглядів 6,273,841

Peter Whidden

Peter Whidden

День тому

Code:
github.com/PWhiddy/PokemonRed...
Discord:
/ discord
Collaborations, Sponsors:
See channel email
Buy me a tuna melt:
www.buymeacoffee.com/peterwhi...
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

КОМЕНТАРІ: 7 700
@deesh6378
@deesh6378 6 місяців тому
An AI being traumatized by using a pc is the most ironic thing I've heard in a while
@mcstrategist
@mcstrategist 5 місяців тому
Haven't you seen twitch plays pokemon? PCs are a death sentence!
@nimi-nae
@nimi-nae 5 місяців тому
I didn't even make that connection 😂
@derrickkamphaus8743
@derrickkamphaus8743 4 місяці тому
@@mcstrategistI remember that. People were spamming. To get rid of pokemon. They had to ban people and make rules. That was pretty hilarious though.
@derrickkamphaus8743
@derrickkamphaus8743 4 місяці тому
@@nimi-naesame. But yeah that’s pretty funny
@Kurayamiblack
@Kurayamiblack 4 місяці тому
Sudden excessive punishment against a curiosity traumatizes first time experiencer Seems all too legit 😅
@markcooper4876
@markcooper4876 5 місяців тому
I laughed so hard when the AI refused to press the A button when it lost.
@MP-lv5vk
@MP-lv5vk 4 місяці тому
Stalling to avoid the outcome confirmation. Reminds me of young children, actually. Haha
@JohnnyNatrium
@JohnnyNatrium 3 місяці тому
@@MP-lv5vk Sometimes the sound of a door slamming because of a gust of wind can remind me of children slamming their hands on a table. There is ZERO connection/homology between anything in the bot produced behavior, and the realm of human motivation or other emotions. It is logically impossible to learn anything about humans from literally everything about this showcase except by observing the actual human who decided to create this mathematical formula of instructions (algorithm) to a low level brute force bot.
@kphaxx
@kphaxx 3 місяці тому
@@JohnnyNatrium Yeah but it reminds me of children's stubbornness lmao
@marcelgonzalez1151
@marcelgonzalez1151 3 місяці тому
Children can be the sorest losers, refusing to keep playing is hilarious 😂
@Loliconman
@Loliconman 3 місяці тому
The only winning move is not to play.
@cappuccinocappy
@cappuccinocappy Місяць тому
I dunno why but the clips were all the AIs aimlessly walk around like a colony of small ants is unbelievably adorable to me
@sugabopp
@sugabopp 28 днів тому
holy shit ai are the ants. or are ants the ai?
@shreyandas4243
@shreyandas4243 День тому
Is this a subtle nod to @SmallAnt ?😂
@Toolazytothinkofagoodhandle
@Toolazytothinkofagoodhandle 2 місяці тому
I’m so glad you didn’t stop when you said “this sounds like a reasonable stopping point”
@BorrisBackyardigan
@BorrisBackyardigan 3 дні тому
But then he stopped not to long after 🥲
@Hitmonstahp
@Hitmonstahp 6 місяців тому
it was unreasonably adorable when the AI stopped in Pallet Town to enjoy the scenery
@azukar8
@azukar8 6 місяців тому
Seconded
@AyaxTheDragon
@AyaxTheDragon 6 місяців тому
The AI is cute
@htspencer9084
@htspencer9084 6 місяців тому
Based AI knows true happiness.
@Trashley652
@Trashley652 6 місяців тому
Ok but did you see the little dance after beating the bug catcher on the first try?
@kratangg-arang
@kratangg-arang 6 місяців тому
Yeessss I envision it talking everything in with a solemn smile, knowing that it’s about to leave this quaint town on a grand adventure of trials and learning. ‘Just one more moment at the banks of this familiar lake, then I’ll be off…’
@butterfish6799
@butterfish6799 6 місяців тому
“The ai is learning how to move, and is just walking around” really explains a lot of my online teammates in first person shooters.
@jeffwooten6888
@jeffwooten6888 5 місяців тому
Bots
@Johnrick90
@Johnrick90 5 місяців тому
Like my team mates in LoL
@hallmark1
@hallmark1 5 місяців тому
Lvl 1 lukes in star wars battlefront 2 hvv
@porkhill6665
@porkhill6665 5 місяців тому
Npcs playing npcs 😢😮
@IschmarVI
@IschmarVI Місяць тому
@@jeffwooten6888"bot" sounds so negative. Maybe we should start calling them "reinforcemenrt learners" instead.
@brandonbrsndon
@brandonbrsndon 2 місяці тому
i love that the AI decided to just hang out and watch the scenery. reminds me of my favorite poem “Stopping by the woods on a snowy evening” by Robert Frost
@piciperkuadrik4636
@piciperkuadrik4636 Місяць тому
Everybody likes Robert Frost
@danielserrano929
@danielserrano929 Місяць тому
I’ve done this many times in my play throughs with Pokémon, it’s actually scary how much the AI “mimics” human behavior.
@aceq361
@aceq361 Місяць тому
​@@piciperkuadrik4636not True I actually HATE Robert Frost
@lateusbetelgeuse
@lateusbetelgeuse 5 місяців тому
Since I'm all into both Pokémon and coding, UKposts suggested your video just minutes after you uploaded it. I subscribed after a few minutes watching it, and now I watched it again and noticed you have almost 50k subscribers! With just one video! Please take that as a public, worldwide testament of the effort you have put into this. Thank you so much!
@DruggiePlays
@DruggiePlays Місяць тому
Broke yt 😂
@t2g648
@t2g648 Місяць тому
If you like Pokemon and AI, you'll love this: ukposts.info/have/v-deo/g4eofnqweX5pyps.html&ab_channel=Spawnvilley
@pengwino828
@pengwino828 7 місяців тому
The ai discovering rng manipulation is mindblowing. I wonder if games in future could use ai to learn tedious or very specific glitches during beta testing.
@antoinecharbonneau5108
@antoinecharbonneau5108 6 місяців тому
They already do!
@NinjaArmy36
@NinjaArmy36 6 місяців тому
Dude it clicked as he was explaining it "wasn't optimal" but also repeating and I was like "NOOOOOOO!!!"
@user-kt6ne3fx6u
@user-kt6ne3fx6u 6 місяців тому
Why bother?
@veto_5762
@veto_5762 6 місяців тому
@@user-kt6ne3fx6u simple, ai thinks and tries things different to a human, it could discover stuff the devs wouldn't even imagine it was possible
@snowolf494
@snowolf494 6 місяців тому
This is an elaborate version of fuzz testing, which is the act of feeding random data to a program to see how it react.
@olemew
@olemew 5 місяців тому
That whole traumatic experience with the PC and the Pokecenter was fascinating. Thank you for making this
@jeremycontreras6229
@jeremycontreras6229 5 місяців тому
The poor AI aww 😢❤
@whirlpoolstudio97
@whirlpoolstudio97 5 місяців тому
It triggered my Twitch Plays Pokemon PTSD
@Spooglecraft
@Spooglecraft 5 місяців тому
the analogies between human behavior and AI behavior were quite interesting in general, though the trauma sticks out. also kinda makes you think about ourselves, doesn't it? after all, this is ultimately just a statistic algorithm with a simple reward system, but it manages to show some rather lifelike emergent behaviors, which weren't inherently programmed it. then again, pretty much all of life is not that different, the model and algorithm are just much bigger and more granular and complex.
@perrowason5096
@perrowason5096 5 місяців тому
Indeed it happened to me when i was young, i didnt know how to withow pkmn bc the storage system was a mess so i didnt use the pc anymore xd
@shanemorris3554
@shanemorris3554 5 місяців тому
Reminds me of the trauma triggered whenever Twitch plays pokemon went near the computer after they accidentally released all those pokemon haha!
@brandonvolesky9867
@brandonvolesky9867 4 місяці тому
Your findings, implementation, logic, and ANIMATION is incredible. 👏👏
@e4e5e2e7
@e4e5e2e7 3 місяці тому
Extremely impressive visualization of the simultaneous iterations. It can be hard to grasp that machine learning is happening in batches of mass parallel attempts, not each progressive scenario after another one by one. Excellent video!
@DolanDarker
@DolanDarker 6 місяців тому
This must've taken an insane amount of time to not only simulate but also edit, really good video, nice work
@MoazSalama-ly5jf
@MoazSalama-ly5jf 6 місяців тому
Omg Dolan you fucking legend where you been
@MrGoodeats
@MrGoodeats 6 місяців тому
rN6media does the edits
@anouaressanoussi
@anouaressanoussi 6 місяців тому
Have you forgotten your password?
@Hawk7886
@Hawk7886 6 місяців тому
​@@anouaressanoussiobviously not
@itsOZone
@itsOZone 6 місяців тому
​@@MrGoodeatsyeah most youtubers dont edit their own content anymore
@Tommybgoode
@Tommybgoode 6 місяців тому
The AI is cool and all, lots of comments discussing it, but. I just wanna say, the editing is so awesome for a video like these, you don't often see such excellent presentation
@Lone.Willow
@Lone.Willow 6 місяців тому
I'm honestly baffled by how this was animated. How did you get the scenes with the thousands of character sprites moving about, all overlapping one another?
@patrickjones3826
@patrickjones3826 6 місяців тому
@@Lone.Willow all is revealed at 26:27
@scotthuber8536
@scotthuber8536 6 місяців тому
200% this. Not only taking on the entire workload of the project, but taking the time making such an enjoyable and informative visual aid is stellar!
@XistenceX1
@XistenceX1 6 місяців тому
​@@Lone.Willow Yeah that's what's wild, the AI stuff is sick, but the editing to show the iterations had me fucking floored.
@maxmuller6730
@maxmuller6730 6 місяців тому
I just thought the same, the presentation is amazing 👏
@elrudiiisimo3066
@elrudiiisimo3066 5 місяців тому
I’m not sure if you noticed this or not Peter, but this is historic. In terms of R&D and just human science. Very impressed with this creativity and passion. Cheers 🥂
@kaComposer
@kaComposer 3 місяці тому
Genuinely blown away by the many high level skills this takes. On top of that, you have an incredible ability to teach high level concepts to a lay audience. Very rare!
@PantheraTK
@PantheraTK 9 днів тому
@@kaComposer Agree. This level of technical ability plus storytelling ability is magnificent.
@willianrocha5475
@willianrocha5475 2 місяці тому
As a Pokemon enthusiast with 4 Pokemon tattoos and a data analyst aspiring to become a data scientist, this project was one of the coolest to watch! I was so fascinated that I decided to replicate the project myself. I encountered some difficulties along the way, but the Discord community was incredibly helpful. Congratulations on the project! 🙌
@kylehill
@kylehill 6 місяців тому
This was extremely well made. Great job
@GameTimeWhy
@GameTimeWhy 6 місяців тому
Holy cannoli it's science boi Kyle "Thor" Hill with his locks in the wild.
@draaaven157
@draaaven157 6 місяців тому
I see we spend our sunday nights similarly. Lmfao.
@buddycal1
@buddycal1 6 місяців тому
This is honestly one of the best endorsements this video could have
@BigBaadMark12
@BigBaadMark12 6 місяців тому
I’m certain the algorithm recommended me this video because of your comment
@Big_Biba
@Big_Biba 6 місяців тому
Its the goat 🐐
@ArmoredarmadilloX
@ArmoredarmadilloX 6 місяців тому
Honestly the AI becoming traumatized from the PC was heartbreaking. Poor lil guy didnt understand what happened
@istumby
@istumby 6 місяців тому
My heart dropped when it was revealed he never went back to the Pokémon center afterwards, I felt so bad for the guy.
@hunterwylie6969
@hunterwylie6969 6 місяців тому
@@istumbyright? Just imagine how rewarding it would’ve been to gain those total levels back! Probably would’ve broken the reward system, as there’s nothing keeping the AI from depositing the Pokémon just to get rewards for pulling it back out.
@Yelonek1986
@Yelonek1986 6 місяців тому
@@hunterwylie6969 Deposit, withdraw, deposit, withdraw like a junkie.
@nousukas
@nousukas 6 місяців тому
"The Pokémon center stole my only squirtle!"
@kdsavage1991
@kdsavage1991 6 місяців тому
Don't feel bad, they learn as they go!
@menerdo
@menerdo 3 місяці тому
5 mil on your first video. Great quality, good research and break down. Congrats, can't wait to see what you bring next!
@McDonaldsCalifornia
@McDonaldsCalifornia 2 місяці тому
Incredibly well made video! I think your resourcefulness and ability to explain things in non-technical terms shows a deep understanding of the topic. Plus the storytelling is top notch
@timothypickarski5234
@timothypickarski5234 6 місяців тому
Not that I don’t love the videos that just say “I applied an AI to this game and here’s how long it took to finish it” but this video (in addition to its high quality visuals and great script) is so much beyond that. Instead of just watching a video on AI, we’re learning about reward implementation, the human condition, curiosity, and more and more. This went above and beyond, I was so rooting for our AI buddy by the end of this lol.
@hciasdhi
@hciasdhi 6 місяців тому
You're right! This feels like an in depth, academic essay
@wiiu-theunderratedconsole7569
@wiiu-theunderratedconsole7569 6 місяців тому
I want to see the AI beating the game
@DigitalIndra
@DigitalIndra 6 місяців тому
"Just hanging out and admiring the scenery, is more rewarding than exploring the rest of the world." Never have I felt more like a machine learning algorithm than this sentence right here.
@harm991
@harm991 6 місяців тому
The digital world is more rewarding than the real world
@ceigey-au
@ceigey-au 6 місяців тому
Very relatable outcome!
@counterleo
@counterleo 6 місяців тому
Me too, why bother capturing and fighting when you can just chill and enjoy the motion of leaves and waves? Quite poetic
@DNAngelOtaku
@DNAngelOtaku 2 місяці тому
how many grew a gambling addiction trying to win an eevee?
@livingdamen4363
@livingdamen4363 Місяць тому
No one since you get it for free as a gift in one of the rooftops lol 😂
@looppooper2306
@looppooper2306 20 годин тому
​@@livingdamen4363 Still six, gambling addiction doesn't work logical 😢
@Lelouch999
@Lelouch999 4 місяці тому
I’m thoroughly impressed by this video. Rarely someone executes an idea to this level of clarity. Visually it is very easy to understand what’s going on as well. Plus you’re sharing the project with everyone. Keep up the hard work
@aylakoch4516
@aylakoch4516 6 місяців тому
This was edited and put together so amazingly well. I haven’t even finished yet- I just needed to express my gratitude that you took the time to not only complete this project but edit the process in such a visibly appealing way. Thanks for 33 genuinely enjoyable minutes!
@dognigga
@dognigga 6 місяців тому
shit was boring asf, felt like a lecture lol
@faith9505
@faith9505 6 місяців тому
A Happy Way to Live The servants who are ready and waiting for his return will be rewarded. -Luke 12:37 All around us we can see fulfilled Bible prophecies, signs indicating that the return of Jesus Christ is drawing near. As followers of Christ, we should be watching for Him. We need to be ready to go. Jesus, speaking about His return, said, “Be dressed for service and keep your lamps burning, as though you were waiting for your master to return from the wedding feast. . . . The servants who are ready and waiting for his return will be rewarded” (Luke 12:35-37) Are you ready for His return? To be ready means to be engaged in activities that you wouldn’t be ashamed to be doing if Jesus were to return. It’s a good idea to periodically ask ourselves this question: This place that I am about to go, this thing that I am about to do, would I be embarrassed if I were doing it when Jesus came back?” Think about your plans. Is there anything you will be doing today, tonight, or tomorrow that you would be ashamed to do if Christ were to return? If so, then change your plans. You want to be ready for His return. Not only should we be ready, but we should anxiously await the return of Christ. We used to have a German Shepherd who slept outside the bedroom, leaning against our door. We didn’t let him sleep in our room because he often had nightmares and would wake us up. Every morning when we opened the door, he rolled into the room. Then he’d jump up and start running in circles. He was genuinely happy to see us. That is how we should be waiting for Christ’s return. And anything that might prevent us from saying “Come quickly, Lord Jesus” is out of place in our lives. In addition to waiting, we should be working. Every now and then, someone predicts that Jesus will return on a specific date. People believe these predictions and start quitting their jobs or divorcing their spouses. But that is not what we should be doing as we wait for the return of Christ. Instead, we should be working for Him. The Bible says, “Just as the body is dead without breath, so also faith is dead without good works” (James 2:26) If watching is the evidence of faith, then working is the evidence of faith in action. Watching for the Lord’s return will help us prepare our own lives. But working will ensure that we bring others with us to Heaven. The great British preacher C. H. Spurgeon said, “It is a very blessed thing to be on the watch for Christ. . . . You can be poor without murmuring; you can be rich without worldliness; you can be sick without sorrowing; you can be healthy without presumption. If you are always waiting for Christ’s Coming, untold blessings are wrapped up in that glorious hope” When you live in the anticipation of Christ’s return, it’s a happy way to live.
@hornoxthekingslayer8100
@hornoxthekingslayer8100 6 місяців тому
If you ever do have the AI finsih the game, I think it would be really cool if you let the same AI try Pokemon Gold. I think seeing if an AI trained on Gen 1 could play Gen 2 that would be an interesting experiment
@zeebo30
@zeebo30 5 місяців тому
Obviously it'd have to relearn how to navigate the map, but it'd probably do well in battles since it already knows how
@johnhamilton5431
@johnhamilton5431 5 місяців тому
It wouldn't be able to catch the farfetchd or use cut This game would fail too with the hm's
@geekygecko1849
@geekygecko1849 5 місяців тому
I'm going to do this as a project for my machine learning class, and I am planning on trying the same algo on Gen 2.
@lpsfoxstar8454
@lpsfoxstar8454 5 місяців тому
do make a video@@geekygecko1849
@MizChivVvOzZz
@MizChivVvOzZz 4 місяці тому
​@@geekygecko1849how can I follow along?
@000glowinthedark000
@000glowinthedark000 4 місяці тому
I can't wait for this project to hopefully continue in the future. This was so well done
@jdllim
@jdllim 6 місяців тому
It's one thing to set all this up, and it's another to visualize and present it in such a coherent and digestible way. You did both so well! Hope to see more content from you in the future
@user-vs3fv1ii1o
@user-vs3fv1ii1o 6 місяців тому
Agreed! This video is insane!
@youngsdiscovery8909
@youngsdiscovery8909 6 місяців тому
I can't believe it's done by individual. Super high quality.
@eddie7252
@eddie7252 7 місяців тому
I honestly expected this video to be from a youtuber with thousands of subscribers, to see that you only have 60 baffles me, this is an incredibly well-made and well-put together video.
@viperific3410
@viperific3410 6 місяців тому
yeah i thought the same, its gone up to 400 now but still nuts
@androsp9105
@androsp9105 6 місяців тому
tbf, it's his first video.
@viperific3410
@viperific3410 6 місяців тому
@@androsp9105 yeah I only realised that after I left this comment, even more nuts lmao
@Station9.75
@Station9.75 6 місяців тому
He’s gained nearly 5,000 in a few days. Very good going.
@AwesomeHairo
@AwesomeHairo 6 місяців тому
Misuse of commas.
@dtolud
@dtolud 4 місяці тому
everything about this video is extremely well done, even the editing , i think big bro is an actual genius
@telprydain1
@telprydain1 3 місяці тому
Such an amazing first video - can't wait to see what you do next.
@fartmicrowave
@fartmicrowave 6 місяців тому
I'm so glad the UKposts algorithm decided to recommend your video and I clicked on it. It's a fascinating thing to watch the process and journey that the AI goes through, while the presentation of the whole video is equally fantastic. Great video, you all deserve a round of applause for the effort and quality put into this whole project.
@BlackScytheLP
@BlackScytheLP 7 місяців тому
Haven't even finished the video yet, but I want this to pop off in the Algorythm, this video had tons of efforts put into it, and deserves to get out there.
@Neo_Data
@Neo_Data 6 місяців тому
I've got some good news for you, that's how I found this video
@esotericraime1441
@esotericraime1441 6 місяців тому
The algorithm brought me here
@auraonline9073
@auraonline9073 6 місяців тому
Guess I'll throw on a comment too then. This is great!
@pionaiz
@pionaiz 6 місяців тому
yesss this was so cool
@aaronhpa
@aaronhpa 6 місяців тому
Thanks then
@kboss1998
@kboss1998 2 місяці тому
This is a masterpiece! I really respect you that made all of these including video editing. What a talent!
@ToGham21
@ToGham21 5 місяців тому
It's a very qualitative video All the screens view and different IA moving make it very pleasant to watch! Thanks
@jondebeer6863
@jondebeer6863 6 місяців тому
As a physicist i appreciate those visualizations. This is truly remarkable content.
@aurelia8028
@aurelia8028 6 місяців тому
wtf does you being a physicist have to do with anything? guess you just wanted attention.
@MichaelCrecker
@MichaelCrecker 6 місяців тому
The AI naming Squirtle “AAAAAAAAAA” killed me! 😂Thanks, amazing content.
@RevanBC
@RevanBC 6 місяців тому
AI picked the Squirtle in Pokemon Red lol what a contrarian
@Tropictopic69
@Tropictopic69 6 місяців тому
i was hoping someone else had mentioned this
@Tyler-qh7bf
@Tyler-qh7bf 6 місяців тому
@@RevanBC that was its only option...
@RevanBC
@RevanBC 6 місяців тому
@@Tyler-qh7bf No you can pick 2 other pokemon! idiot.
@sergeantjoe6802
@sergeantjoe6802 6 місяців тому
Pigeoto was ‐-----------
@Prince_Oli
@Prince_Oli 3 місяці тому
I cannot believe i am actually watching this intently. Its so fascinating! And how you apply the AIs experiences with that of a human's experience in the real world is exceptionally well done. Good job mate!
@songofalchemy
@songofalchemy 4 місяці тому
Insanely well made video, rare that I want to go out of my way to share videos with people but this is really impressive. Lots of extra "human lessons" in here that you glossed over, like the Pokémon Center trauma for example. Super good man
@turingtestingmypatience
@turingtestingmypatience 6 місяців тому
watching the little reds go round like an ant colony brings me so much joy and i don't know why. look at them all exploring. learning. discovering the world. lil guys. thank you for spending at least 1000USD and several hours putting this together just for me to uncontrollably laugh at the reds for 20 minutes ..with that out of the way, fantastic video. incredibly readable visuals and clear voiceover, awesome topic, understandable for several levels of previous knowledge. can see this hitting the high hundred thousands.
@raula6533
@raula6533 6 місяців тому
I was looking for this comment because I thought the same!!! It was like watching ants!! Just amazing!! This video exploded my mind... Imagine a Pokemon game were you can compete against a real "rival" (blue) in real time just to see who wins the league first... And every run the rival gets different pokemons with different moves... This guy is just insane, this is like a Pandora box!!!! New sub for sure!!!! And thank you for this video Peter!!!!!
@user-io6ww9uv7e
@user-io6ww9uv7e 3 місяці тому
This might be the coolest video of AI playing a video game I've ever seen. I love all the fascinating emergent behaviours (especially the RNG manipulation), as well as the analogies you draw to humans. I also love that you presented the technical explanations in a way that allowed me understand almost everything without any programming knowledge, just a decent understanding of AI. Genuinely amazing job, I hope to see more like this in the future! :)
@yusukeurameshi500
@yusukeurameshi500 3 місяці тому
We need more! this was so fascinating, informative and entertaining. I hope your able to make an ai finish the game one day, it would make for one hell of a video! Thank you!!
@steven-mz3jf
@steven-mz3jf 6 місяців тому
Seeing high effort videos like these from relatively low sub channels always surprises me. Definitely deserves more recognition/subs.
@napoleonbonerfarte6739
@napoleonbonerfarte6739 6 місяців тому
It's the only video on bro's account lmfao wdym
@RandyGBH
@RandyGBH 6 місяців тому
@@napoleonbonerfarte6739lol was about to write this too
@abhishekkoundal584
@abhishekkoundal584 6 місяців тому
Good things take time
@absolutelyfookinnobody2843
@absolutelyfookinnobody2843 6 місяців тому
And people who over react to low sub channels being high quality doesn't surprise me. Lots and lots of dumdums out there
@SplishySploshy
@SplishySploshy 6 місяців тому
As a psych prof I'm always trying to think of different ways to explain certain concepts and give relatable examples, and this one is perfect!
@MasteringSilence
@MasteringSilence 6 місяців тому
They tell me I’m crazy here 🤪
@norabarlow17
@norabarlow17 6 місяців тому
​@@MasteringSilenceCrazy? I was crazy once
@MasteringSilence
@MasteringSilence 6 місяців тому
@@norabarlow17 you only lose your mind once… They put me in a rubber room with rubber rats…
@knockout8157
@knockout8157 6 місяців тому
@@norabarlow17they locked me in a room. A rubber room with rats.
@charpool169
@charpool169 6 місяців тому
As a psych professor can you explain the appeal to these people repeating the copy paste comments? Also just to be clear I'm also asking out of genuine curiosity if there may be psychological reasons past the basic wanting to be a part of something, and not just trying to hate on them or anything ✌
@ideannassiri9672
@ideannassiri9672 2 місяці тому
this man releases a single video in his career and makes the front page, keep the sick vids coming clearly a big name in the making dude you got this
@dala555
@dala555 2 місяці тому
1 video, 55k subs, 5.7M views. This is historic
@dead0barbie
@dead0barbie 2 місяці тому
superb video, text and learning, good job! Also, on the relatableness of experience, occurrences and patterns, there's memetic we use now more than ever to render perceptible the archetypal moment in videogames where a point of inflection occurs and hold a certain humour that we choose to transmit via memes later on.
@BryceHuston
@BryceHuston 6 місяців тому
They told me my Pokémon phase would pass. Little did they know, it was just evolving into an AI obsession!
@sanjaywilson8232
@sanjaywilson8232 5 місяців тому
Pokémaniac Bryce Huston wants to battle!
@ashashii911
@ashashii911 5 місяців тому
​@@sanjaywilson8232LMAO!
@30303Steve
@30303Steve 4 місяці тому
*Pokemon Trainer Battle Theme starts playing*
@821aq
@821aq 3 місяці тому
Edit : Go Lucario ! Fight Pokemon Bag Run away
@LPcrazy_88
@LPcrazy_88 6 місяців тому
Holy crap this is your very first YT video? I can't wait to see what you cook up if you continue to create! Outstanding work!
@clickpwn
@clickpwn 6 місяців тому
Tbh I didn’t know youtube algorithm allowed channel with 1 video to pop off like this. Over 1 million views in 7 days?? If this video was posted in a sizable channel, it might have been even 10 times more.
@bilibangbang
@bilibangbang 6 місяців тому
he paid for the view XD@@clickpwn
@sarkhaaan
@sarkhaaan 6 місяців тому
@@bilibangbanghow you know that?
@stonybaboon
@stonybaboon 6 місяців тому
It gets better when u go into the git-hub project and find out that he has been working on this for the last 2 years...
@blake..-
@blake..- 6 місяців тому
@@bilibangbangmald
@blindcatdonovan229
@blindcatdonovan229 5 місяців тому
That reinforcement training for AI is technically the same as pure clicker training (positive reinforcement) for animals, where you have to train them by only rewarding tiny steps torwards the goal. Anyone being advanced in that field would be a great choice to give ideas for how to train those AIs
@MrCmon113
@MrCmon113 3 місяці тому
I think that's more like curriculum learning. In the purest form of reinforcement learning you don't encode your knowledge on how to solve a problem in the reward function.
@mateuscrevelin3394
@mateuscrevelin3394 4 місяці тому
First and only video of the channel and it already is a banger like this... Great work there amigo. Btw. I really appreciate you leaving the project opensource. I hope I can improve it in some way in my own experiments...
@flicmylich
@flicmylich 6 місяців тому
Bro honestly this is UKposts video of the year. How spectacularly you presented this information in such a clear and entertaining way that is honestly on the level of professional science productions like Cosmos. Absolutely colossal performance man. I wouldn’t be surprised if you had an entire production team.
@peterwhidden
@peterwhidden 6 місяців тому
thank you for the kind words :) no production team, but my friend @torinblankensmith made the thumbnail
@lovol2
@lovol2 6 місяців тому
I second this. I'm super interested in the content, but at the same time I'm like.... However did he make this look so good.
@glupshitto1977
@glupshitto1977 6 місяців тому
It’s not that deep dude holy shit
@Tom-yg7mi
@Tom-yg7mi 6 місяців тому
@@glupshitto1977 its deep.. learning.
@Fissan_Poulsen
@Fissan_Poulsen 6 місяців тому
@@Tom-yg7mi get out
@chrispyvolterra
@chrispyvolterra 6 місяців тому
This is their first UKposts Upload, it’s crazy to me how much work, effort and money went into its production without having built an audience on an already successful channel before. Mad props to you Peter.
@chrispyvolterra
@chrispyvolterra 6 місяців тому
I am looking forward to see what else you will create.
@notavailable947
@notavailable947 6 місяців тому
He is an employee of Amazon Headquarters in Seattle 👏🏽👌🏽 He is smart af
@woodybutler
@woodybutler 4 місяці тому
The fact you walk through running everything for everyone else is so generous. Thanks!
@QoStoOds
@QoStoOds 4 місяці тому
Breaking down some really cool tech for the layman just earned you another sub! Great video mate 👍
@matteoemanuele-gi4jk
@matteoemanuele-gi4jk 6 місяців тому
Fellas, I'm an AI engineer, with a short background in Reinforcement Learning for a period I interacted with Sony for a job. I need you to understand the MAGNITUDE of these results. It's an insane work, and I'm sad that probably only a few might understand the sheer amount of skill require to do this. Insane job man, you are a goat
@dkm9090
@dkm9090 6 місяців тому
This is no understatement . This takes a level of focus and problem solving that is just not normal. Savage!
@bricegardner7815
@bricegardner7815 6 місяців тому
I’m not even an engineer, and my jaw is on the ground. I genuinely would love to learn how to become a part of this world. I wish there were more people in my circle with hobbies and fascinations like this. I used to help write xml codes for world of Warcraft bots when I was a kid. Now laying in bed with an alarm set for five hours from now. I’ve got a sales job… is 33 years old too old to learn how to work in this scene? This video drips with knowledge, and a wisdom and understanding of something that I have no idea how to even begin to approach. Kudos!!
@alr9447
@alr9447 6 місяців тому
I wouldnt say those results are impressive theory wise ? The impressiveness of the work comes from a technical point of view, how great he managed to link the RL model with the game and the fine-tuning he put in it. By the way, AI engineer doesnt really mean anything, what is your job title ? Out of curiosity
@harshrajjadhav940
@harshrajjadhav940 6 місяців тому
​@bricegardner7815 no age is too high. With enough determination and curiosity you can definitely pivot. Look into videos explaining the skills required to get a job in game development/ AI.
@matteoemanuele-gi4jk
@matteoemanuele-gi4jk 6 місяців тому
@@alr9447 I am officially a data scientist, but within the team I'm the guy responsible of the training of the ML models, therefore I make this distinction because nowadays "data scientist" is too broad. In most big tech companies, AI engineer is a common notation to distinguish between the data science folks
@joshuasims5421
@joshuasims5421 7 місяців тому
That was incredible! I’ve always wondered if this was possible, I’m blown away by what the AI was able to learn! The visualizations and presentation were excellent, I hope this video reaches a wide audience!
@MrRaveHaven
@MrRaveHaven 3 місяці тому
Amazing model organization and execution, amazing post production, amazing communication of novel and or complex concepts in a way everyone can understand. Well done and well worth the multi million likes you’ve gotten
@Liquid_Joe
@Liquid_Joe 3 місяці тому
Very impressive. I'm looking forward to any future content you upload
@dralinkushinen
@dralinkushinen 6 місяців тому
Just 10 minutes in, and it has already gotten so damn interesting! The behaviors, the systems, the events, the unexpected but explainable scenarios, the AI literally experiencing something comparable to trauma? I want to see more!
@kaelthunderhoof5619
@kaelthunderhoof5619 6 місяців тому
The Red swarm wasn't enough?
@kaio0777
@kaio0777 6 місяців тому
me too sad when he stop at moon mt.
@Elintasokas
@Elintasokas 6 місяців тому
The AI doesn't experience anything because it's not a conscious entity. It experiences as much as Microsoft Word when you open it.
@alexb8926
@alexb8926 6 місяців тому
@@Elintasokas😅😂😂
@JamanWerSonst
@JamanWerSonst 6 місяців тому
@@Elintasokas Based on my PCs heavy breathing when I open Word I assume its orgasming.
@trbremm
@trbremm 6 місяців тому
I really like how grounded and transparent your breakdown of the AI capabilities and limitations is, it shows it as a tool and not as a magical solve-all-problems strategy. Also, what a masterful storyteller and explainer you are. This video is very well paced and laid out, congrats!
@SSGoatanks
@SSGoatanks 6 місяців тому
Yes it's limited but imagine what it could become in a few more years 🤖
@zxuiji
@zxuiji 4 місяці тому
12:34, You coulda just added a reward for "foe damaged" and directly added the damage dealt as a reward, this would've encouraged it to try other moves the moment it sees that reward occur via any battle. Could've also added a penalty for move depletion, with bigger losses for the more expensive moves, encouraging it to balance move usage.
@HieronymousLex
@HieronymousLex 3 місяці тому
I’m guessing the first suggestion would make the AI just stay and constantly battle Pokemon in the first area
@zxuiji
@zxuiji 3 місяці тому
@@HieronymousLex Hadn't thought of that, but yeah I guess the penalty for move depletion would deal with that by accident
@SpecialJess2
@SpecialJess2 2 місяці тому
​​​@@HieronymousLexif in New tile give points for super effective 30s cooldown after battle
@Distractionn-CG_5945
@Distractionn-CG_5945 18 днів тому
This was absolutely amazing, my friend! Please do more of these! I must admit I was disappointed that you didn't do the whole game 😂
@Solsumi
@Solsumi 6 місяців тому
Dropping a comment to help the algorithm. This video honestly deserves millions of views. I love the part where the AI learned to RNG manip to catch a Rattata. It's one of those moments that's unexpected at first but when you go back and look at it it's like, "oh, of course it would react like that!" Moments like those are why I love AI learning videos like this.
@Hateburn
@Hateburn 6 місяців тому
I remember back when there were 1 or 2 reinforcement learning videos on YT. Now we get all sorts. But this one...this one is special. The production value here is excellent. Thanks for all of your hard work.
@William_ben_chan
@William_ben_chan 2 місяці тому
Very amazing video!!I can't wait to see the next episode!! I'm looking forward to seeing what other interesting things will happen when the AI reaches the end of the game.
@AnAfinityForKarma
@AnAfinityForKarma 2 місяці тому
This was so much fun to watch, and I have no idea how it works - that’s all you buddy, fantastic quality of video. Really looking forward to seeing an AI speedrun in this format if it’s even possible 😊
@henriquemagalhaessoares8739
@henriquemagalhaessoares8739 6 місяців тому
This was an amazing project and explanation. You should submit this to The Journal of Geek Studies if you don't have a publication lined up already.
@seveneyes77
@seveneyes77 6 місяців тому
Wah is that a thing?
@henriquemagalhaessoares8739
@henriquemagalhaessoares8739 6 місяців тому
@@seveneyes77 Yep! They are an online publication that uses geek culture as a way to popularize science. They had a bunch of articles from the biology if final fantasy monsters to the effectiveness of super man disguise.
@RageAgainstTheTards
@RageAgainstTheTards 6 місяців тому
This was awesome, I'd love to see a full series of the AI completing the game.
@user-pv4cw3du2p
@user-pv4cw3du2p 6 місяців тому
Yes!!
@tsunalein
@tsunalein 6 місяців тому
downloaded it and train the ai more
@cassidy8307
@cassidy8307 6 місяців тому
And then i'd like to see it completing the game as fast as possible. An AI speedrun competition: winner gets 100,000 arbitrary points
@freshcupofjoel3000
@freshcupofjoel3000 18 днів тому
More more more! What an outstanding first video! Can't wait for more from you!
@NaudVanDalen
@NaudVanDalen 4 місяці тому
This video is amazing! The AI part must have taken hundreds of hours or even over 1000 and the editing must have taken dozens of hours. Almost 5 million views and 50k subscribers in 2 months is a lot and well deserved.
@JoaoMorais-ee1oq
@JoaoMorais-ee1oq 6 місяців тому
Everything about this was amazing, the computational approach, the video edit, the tone, the explanations and the real life parallels. Beautiful work!
@plasmakitten4261
@plasmakitten4261 6 місяців тому
This is like such a classic example of how AI thinks differently from humans. It can't figure out how to get past a ledge but its pattern recognition is so strong that it figured out friggin RnG manipulation by itself.
@NikhilAutar
@NikhilAutar 6 місяців тому
We humans also have reward systems. Everything "living" does. It's different to an AI model. But who's to say that we're not just an AI model with different base rewards?
@plasmakitten4261
@plasmakitten4261 6 місяців тому
@@NikhilAutar The term "artificial" is meaningless unless it's being used to mean "made by humans". Since we didn't design ourselves, we aren't AI by any useful meaning of the term. But at the core, this way of designing AI is designed to mimic how humans learn, so you're not far off.
@ryanwirawan5012
@ryanwirawan5012 6 місяців тому
Not only the pokemon gains EXP points, the AI gains EXP too
@NikhilAutar
@NikhilAutar 6 місяців тому
@@plasmakitten4261 We'd be artificial to whoever designed us/this haha
@cs16Tactics
@cs16Tactics 6 місяців тому
I think completely opposite :D This (video) was prime example of how phenomenons that happens with humans can be put into numbers used by AI learning. Our learning = pattern recognitions based on the rewards we've gotten. They aren't as vivid with "Getting 3 points on catching pokemon", but rather intuitive that happens automatically.
@fredv9140
@fredv9140 3 місяці тому
This video was fantastically made video. Thank you for this awesome visualisation of a complicated topic. Respect to everyone involved in this x
@SelfSimilarJosh
@SelfSimilarJosh 3 місяці тому
Phenomenal video with wonderful visualizations, great practical comparisons, and great educational content. No doubt, you've inspired many people to learn more about AI.
@thermonuclearwarhead
@thermonuclearwarhead 6 місяців тому
The accidental traumatic depositing of Pokémon in the center is rather hilarious, and the Magikarp/fast food analogy is beautiful. Picking left is an ancient gaming trick, not surprised AI picked it up/that we make games that reward it. And lastly the short-term memory bit seems to me a great idea to solve this (and also, accidentally, rather human :P).
@counterleo
@counterleo 6 місяців тому
I was feeling sad for the AI who must have thought it accidentally killed its Pokémon 🥲😂
@lesbo37
@lesbo37 6 місяців тому
The only flaw in the fast food analogy is we'd need to learn that in the future eating fast food will make you live longer (or something else awesome) given what Magikarp evolves into!
@teenslayer
@teenslayer 6 місяців тому
i thought the traumatic experience was super interesting too and funny lol
@benjones8779
@benjones8779 6 місяців тому
Not sure if its been said already, but, I would love to see them beat the game. Then we can see what levels they got to and what they thought was the best pokemon to have for the elite 4. Would be interesting.
@Asidders
@Asidders 6 місяців тому
Charizard with Slash, easy
@teracraged320
@teracraged320 6 місяців тому
This will took a looooott of time and video preparation edit etc. But I agree would be awesome
@Mcobange
@Mcobange 6 місяців тому
i really doubt if the AI can solve the Stone Moving "Puzzles" inside the IceCave and VictoryRoad thou. Can it even be teached to learn and use the VMs? but id love to see it :D
@davidfl4
@davidfl4 6 місяців тому
I think it would be hard to program the rewards to get them through the specific obstacles tho like using cut in certain places etc
@stephenh9483
@stephenh9483 6 місяців тому
Yeah they would shatter Wersters Speedrun World Record!
@pumpkinkingbones
@pumpkinkingbones 2 місяці тому
As much as I love everything in your video and the time/thought you put into it, I’m also glad you got a large amount of views and subscribers. Something with this much effort deserves appreciation no matter how small or large a channel is. The fact this is your first video for this channel inspires me a lot to continue editing my own videos, despite the time it takes to get it done. I hope to follow your journey as you come out with more videos like this, keep it up!
@Fire_AJ_
@Fire_AJ_ 3 місяці тому
This was really amazing and fun to watch! Immense amount of respect for the hard work you put in!!
@SevereMalfunction7
@SevereMalfunction7 6 місяців тому
this is honestly worthy of an entire course's final project at the graduate level. Thank you for making this freely available!
@warmcat
@warmcat 6 місяців тому
Isn’t it just! I’m currently half way through my final project for my MSc, with a relatively shit regression model predicting energy usage. 😂
@cashmoneybanks8442
@cashmoneybanks8442 6 місяців тому
Did you edit this yourself? Not only is the content amazing, but I'm blown away by how well this was all put together and demonstrated. If this is really your first video that's seriously impressive
@caderlocke8869
@caderlocke8869 6 місяців тому
My first thought when it panned out. Like who tf is this guy lol
@MrGoodeats
@MrGoodeats 6 місяців тому
He used JRGMediaYT for the edits
@rtm3530
@rtm3530 6 місяців тому
He probably asked an AI to edit it 😅
@jonathanlunger2775
@jonathanlunger2775 3 місяці тому
I love this video, idk what you have planned for the future of this channel, but I can't wait to see it!
@user-es8dp4xf2e
@user-es8dp4xf2e 2 місяці тому
An awesome video my dude! Had a great time watching it. The editing is top notch as well as the overall presentation. Thank you! Keep making great videos:))
@AMNEZ1A
@AMNEZ1A 6 місяців тому
This video reminds me of when I got Pokemon Yellow as a kid, I didn't read/speak english so I just had to try things to learn what everything did and was. It's weird how similar the AI playing feels to my experiences as a kid. The Pokemon games (among TV and other games) actually helped me learn english at the age of 9 far before my classmates could and as a little extra ROM hacking got me into graphic design and coding/web development somehow. Pokemon in general is the base of my origin story.
@kaio0777
@kaio0777 6 місяців тому
damn bro that is deep.
@Edoss98
@Edoss98 6 місяців тому
Me with Spanish at 3 years old and English at 2 ahah Pokemon Azul and Pokemon Red 😅
@joaofernandes6349
@joaofernandes6349 6 місяців тому
When I first played Pokemon, just like yourself I was still a kid didn't know any English so I couldn't even save. The first few months was just like the AI, start from that little room and trial and error.
@2006HondaCivicD
@2006HondaCivicD 6 місяців тому
Hello fellow ESL player, i was like 5 when I got my first hand on pokemon. I was EXTREMELY upset when I accidentally start over the game (the copy was second hand and the saved file is from my older brother who already completed the game.) that I cried. I lost my brother's charizard, even the moltres he caught with an ultra ball because i couldnt understand a lick of English back then - overwriting his save accidentally, and I just love exploring the pokemon world more than battling them. Only then 3 whole years later when I did restart and beat pokemon on my own, around 12 I became competently aiming to "gotta catch em all".
@3ountyhunter
@3ountyhunter 6 місяців тому
Is this really your first video?! This is incredibly well done. So glad YT has recognized that your content is deserving of being pushed algorithmically.
@elizabethburns-gundel1052
@elizabethburns-gundel1052 5 місяців тому
I love how you equated the AI actions with human actions. This was fascinating. Great editing work.
@Myla-zl4jv
@Myla-zl4jv 5 місяців тому
I absolutely love you bringing up the parallels to human evolution and psychology. We really can learn a good bit about ourselves through ai
@rainwatervideography4546
@rainwatervideography4546 6 місяців тому
This video was done incredibly! A perfect demo of and comparison to deep learning. A well earned follow. The dedication, creativity, and in depth descriptions are beyond impressive for this being the first video on this channel. Keep at it! I'll be looking forward to what ever you produce next!
@jay.c2097
@jay.c2097 6 місяців тому
Can’t believe this is your first video. This was so entertaining to watch and the editing leaves me wondering how much time it took you. Hope you put out more videos like this and I’d love to see a full AI playthrough at some point!
@Deusregere
@Deusregere 6 місяців тому
I was kinda disappointed that it didn’t conclude with the AI defeating the Elite 4 😢
@aaronsmith4113
@aaronsmith4113 2 місяці тому
incredible video editing and above all research. well done :D
@jmarriottc
@jmarriottc 2 місяці тому
Great stuff man, super informative and a nice way to wrap people's head around machine learning and ai
@ChacalLoL
@ChacalLoL 5 місяців тому
As a Data Scientist, this was amazing to watch :) well done !
@antonioiniguez1615
@antonioiniguez1615 3 місяці тому
I wanted to be a Data Scientist then I realized I couldn't code😂
@TailsMiles249
@TailsMiles249 6 місяців тому
The amount of work you've put into this is so incredible. All of the self recording of _all_ of the AI iterations meant time spent (never wasted) for the sake of a single video. From the editing you've shown down to the research of how the human psyche works, this is beyond something I would even think to produce. You will go far in your endeavors.
@MageMinionsOP
@MageMinionsOP 6 місяців тому
This guy's first video and it's about using ai, so UKposts AI said "I gochu"
@Selxis
@Selxis 3 місяці тому
As a physician working in the field of pathology one of my main tasks is digital microscopy, aka working with medical imaging. AI and machine learning is a huge emerging discipline in our field. This video was very informative as well as entertaining. Thank you. You definitely earned a like and sub from me. Also, as a side note, I couldn't help but associate some of your observations in machine learning with human evolution as a concept. Definitely interesting stuff.
@CarlosMartinez-jn2cf
@CarlosMartinez-jn2cf 2 місяці тому
What gem of a video, beautiful animations, you explained it so well! AMAZING!
@memetech-
@memetech- 6 місяців тому
"ooh, what's this place?" "deposit Pokemon?" "AAAAAAHHHHHHH" *never returns*
@BernardoMachado
@BernardoMachado 6 місяців тому
This is one of the best implementation and visualization videos on the subject I've ever seen. Amazing work!
@Spuddy987
@Spuddy987 2 місяці тому
This is cool. I’ve seen plenty of these ai videos on different games but this one has gone the most in depth to the technical side of it. I am very interested in learning more now
@timbot98
@timbot98 4 дні тому
Thank you so much for sharing this video! You clearly put so much effort in doing the experiments and also in preparing this quality youtube video to explain your results!
@mischavandenburg
@mischavandenburg 6 місяців тому
“Just hanging out and admiring the scenery is more rewarding than exploring the world” Amazing work Peter! I look forward to see how this will progress
@headyshotta5777
@headyshotta5777 6 місяців тому
this video is mindblowing. I have absolutely no clue how you collected and translated all this data into such cool visualizations, but i am in awe. this is so cool. thank you so much for making it!
The Biggest CHEATER in Pokemon History was Finally Caught
35:55
Abyssoft
Переглядів 2,2 млн
The Fastest Maze-Solving Competition On Earth
25:22
Veritasium
Переглядів 18 млн
船长被天使剪成光头了?#天使 #小丑 #超人不会飞
00:28
超人不会飞
Переглядів 27 млн
маленький брат прыгает в бассейн
00:15
GL Show Russian
Переглядів 1,2 млн
skibidi toilet 73 (part 2)
04:15
DaFuq!?Boom!
Переглядів 27 млн
14 Obscure Secrets in Gen 1 Pokémon!
9:37
SmithPlays Pokémon
Переглядів 1,4 млн
AI Learns Insane Monopoly Strategies
11:30
b2studios
Переглядів 10 млн
I beat Pokemon's Hardest Challenge (Kaizo Ironmon)
34:42
SmallAnt
Переглядів 4,4 млн
I tried to make a Valorant AI using computer vision
19:23
River's Educational Channel
Переглядів 1,3 млн
The Pokemon Iceberg
32:39
WolfeyVGC
Переглядів 1,6 млн
Training an unbeatable AI in Trackmania
20:41
Yosh
Переглядів 12 млн
I Survived 100 Days As A Gym Leader In This Pokemon Game
31:18
HDvee Plays
Переглядів 1,9 млн
I Completed Pokemon Emerald's RIDICULOUS Pokedex
51:40
Johnstone
Переглядів 1,2 млн
Much bigger simulation, AIs learn Phalanx
29:13
Pezzza's Work
Переглядів 2,5 млн
Бюджетная видеокарта за 5000 рублей
17:47
Nitroxsenys
Переглядів 34 тис.
Start from 0 at any point on the T1 Digital Tape Measure
0:14
REEKON Tools
Переглядів 31 млн
Опасная флешка 🤯
0:22
FATA MORGANA
Переглядів 727 тис.
Vortex Cannon vs Drone
20:44
Mark Rober
Переглядів 13 млн
Airpods’un Gizli Özelliği mi var?
0:14
Safak Novruz
Переглядів 399 тис.