Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Training AI to Play Pokemon with Reinforcement Learning by Peter Whidden github: youtube:

AK

514,935 subscribers

837,837 views • 2 years ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

Madotsuki.eth (🐍,🍄)2 years ago

@computerender My favorite part of this was the AI discovering RNG manipulation in order to ensure that it presses the very specific sequence of inputs to capture the first encountered Rattata with its first Pokeball 100% of the time. Once it learns that it can do that, it keeps on.

TnvMadhav2 years ago

@computerender Apart from this amazing use-case, the video quality was top tier. Felt like a documentary. Kudos to the creator 🙇‍♂️

Mo El-Bibany2 years ago

@computerender how long until it discovers the rare candy trick??

TAYLOR.WTF2 years ago

@computerender This might be the most beautiful thing I’ve ever seen. 😍

Greg Charles2 years ago

@computerender One of the coolest and nostalgic RL applications I’ve seen

Ezra2 years ago

@computerender Anyone else notice the one instance of Ash who walks up to the tree and stays there, even as other versions of himself split off and leave? Is he stuck or reaching a state of buddhist enlightenment akin to the wall gazing ZaZen buddhists?

Neuromind 👁2 years ago

@computerender Beautiful! 💓

alx.eth2 years ago

@computerender I wonder if it will find the Mew under the Truck.

わわ2 years ago

@computerender Reinforcement Learning by fishes @Mutekimaru_ch

angel ● online2 years ago

@computerender I remember setting up a mod to auto-fish and battle, but now 😈

Related Videos

DeepMind training bipedal robots to play soccer using deep reinforcement learning.

DeepMind training bipedal robots to play soccer using deep reinforcement learning.

MachinePix

16,988,388 views • 3 years ago

Frontier models that use reasoning to "think" during inference are generating 5X more AI tokens per year. ✨ "Inference is now a thinking process. And in order to teach AI how to think, reinforcement learning and very significant computation was introduced into post-training," said NVIDIA CEO Jensen Huang in a recent keynote at #CES2026. Reinforcement learning is increasing computation demands across all AI scaling laws: pre-training, post-training, and test-time scaling. Learn more about reinforcement learning and AI scaling ➡️

Frontier models that use reasoning to "think" during inference are generating 5X more AI tokens per year. ✨ "Inference is now a thinking process. And in order to teach AI how to think, reinforcement learning and very significant computation was introduced into post-training," said NVIDIA CEO Jensen Huang in a recent keynote at #CES2026. Reinforcement learning is increasing computation demands across all AI scaling laws: pre-training, post-training, and test-time scaling. Learn more about reinforcement learning and AI scaling ➡️

NVIDIA AI Infrastructure

13,329 views • 6 months ago

Redwood AI | Mobility Reinforcement Learning

Redwood AI | Mobility Reinforcement Learning

1X

1,322,570 views • 1 year ago

i trained a reinforcement learning agent to play diablo 1 in a few hours with pufferlib

i trained a reinforcement learning agent to play diablo 1 in a few hours with pufferlib

Dan Advantage

41,954 views • 8 months ago

Developed by a Swiss-led team, a robot uses reinforcement learning, a type of AI that improves decision-making through repeated attempts to play badminton against human opponents

Developed by a Swiss-led team, a robot uses reinforcement learning, a type of AI that improves decision-making through repeated attempts to play badminton against human opponents

Reuters

56,015 views • 1 year ago

"We have maybe the same size cake, and we just want to crush it with a giant reinforcement learning cherry." OpenAI's Dan Roberts discussed the controversial shift to prioritizing RL over pre-training at AI Ascent.

"We have maybe the same size cake, and we just want to crush it with a giant reinforcement learning cherry." OpenAI's Dan Roberts discussed the controversial shift to prioritizing RL over pre-training at AI Ascent.

Sequoia Capital

18,285 views • 1 year ago

Super excited to launch a new AI course! 🚀 Fine-Tuning & Reinforcement Learning for LLMs: Intro to Post-Training A collaboration between AMD 🤝 Andrew Ng’s DeepLearning.AI to give every developer the tools & compute to work with the same post-training techniques, used across today’s leading AI labs. 🎓 Learn for free → 🧵

Super excited to launch a new AI course! 🚀 Fine-Tuning & Reinforcement Learning for LLMs: Intro to Post-Training A collaboration between AMD 🤝 Andrew Ng’s DeepLearning.AI to give every developer the tools & compute to work with the same post-training techniques, used across today’s leading AI labs. 🎓 Learn for free → 🧵

Sharon Zhou

20,386 views • 9 months ago

Sexy soft steps.Adam learned to walk like a human,trained by reinforcement learning.

Sexy soft steps.Adam learned to walk like a human,trained by reinforcement learning.

CyberRobo

19,732 views • 1 year ago

Reinforcement learning experiments continues. Still a bit janky, but it is clearly learning something. This is about an hour into training.

Reinforcement learning experiments continues. Still a bit janky, but it is clearly learning something. This is about an hour into training.

Dennis Gustafsson

22,642 views • 11 months ago

Its nice to see the recent excitement around Q-learning! Here's a clip from a video all about Deep Reinforcement Learning, including Deep Q Learning #machinelearning #ai

Its nice to see the recent excitement around Q-learning! Here's a clip from a video all about Deep Reinforcement Learning, including Deep Q Learning #machinelearning #ai

Steven Brunton

164,997 views • 2 years ago

Baby steps towards physically based animation with reinforcement learning...

Baby steps towards physically based animation with reinforcement learning...

Dennis Gustafsson

32,132 views • 1 year ago

Excited to partner with Cassyni to generate citable DOIs for my videos!!! Example: if you want to cite my video on Reinforcement Learning DOI Youtube Check out the complete collection

Excited to partner with Cassyni to generate citable DOIs for my videos!!! Example: if you want to cite my video on Reinforcement Learning DOI Youtube Check out the complete collection

Steven Brunton

36,044 views • 3 years ago

🎙 New episode of the DeXe Podcast is live! Hosted by Sergio K, this episode features Shashank | 𝔽rAI from Fraction AI, a leading builder in decentralized AI. We talked about: • How decentralized models help train AI through competition and reinforcement learning • Tokenization, governance, and ownership of AI agents • AI future, impact, and limitations 🔴Watch on YouTube: 🎧 Listen on Spotify: Curious about the future of AI training, ownership, and governance and how it all merges with blockchain? Tune in to the full episode!

🎙 New episode of the DeXe Podcast is live! Hosted by Sergio K, this episode features Shashank | 𝔽rAI from Fraction AI, a leading builder in decentralized AI. We talked about: • How decentralized models help train AI through competition and reinforcement learning • Tokenization, governance, and ownership of AI agents • AI future, impact, and limitations 🔴Watch on YouTube: 🎧 Listen on Spotify: Curious about the future of AI training, ownership, and governance and how it all merges with blockchain? Tune in to the full episode!

DeXe Protocol

30,393 views • 1 year ago

how to learn something from the first principles (with a live demo on reinforcement learning)

how to learn something from the first principles (with a live demo on reinforcement learning)

Ajeet ( opensox.ai )

232,836 views • 2 months ago

RL-100 Performant Robotic Manipulation with Real-World Reinforcement Learning

RL-100 Performant Robotic Manipulation with Real-World Reinforcement Learning

AK

15,364 views • 9 months ago

Leemon Baird on merging Hedera's DLT with with AI and how data could one day be monetized for AI usage:"My PhD was originally in AI, it was reinforcement learning.""It's just exciting to see it come full circle." $HBAR

Leemon Baird on merging Hedera's DLT with with AI and how data could one day be monetized for AI usage:"My PhD was originally in AI, it was reinforcement learning.""It's just exciting to see it come full circle." $HBAR

ALLINCRYPTO

12,464 views • 1 year ago

At Flower AI Summit 2025, T-Rize showcased Rizemind: blockchain-powered federated learning with transparent rewards. See how we secure and monetize AI training—full demo on our YouTube channel.

At Flower AI Summit 2025, T-Rize showcased Rizemind: blockchain-powered federated learning with transparent rewards. See how we secure and monetize AI training—full demo on our YouTube channel.

T-RIZE

16,990 views • 1 year ago

notes on my reinforcement learning for rocket league side quest so far: i’m in awe that — we live in a time where i can train a reinforcement learning model that is learning to play rocket league and at the same time, test community made rocket league models. where, both processes can run in parallel & locally on my hardware. in the game window — i’m playing against a reinforcement learning ppo model that’s running locally. and in the vscode window — i’m training my own reinforcement learning model (just a dummy example script for now). also, the rocket league botting ecosystem has incredible tooling where you can test out different reinforcement learning ideas against other algorithms + it has great documentation for linux and windows. it’s honestly a beautiful hidden gem of a rabbit hole :)

notes on my reinforcement learning for rocket league side quest so far: i’m in awe that — we live in a time where i can train a reinforcement learning model that is learning to play rocket league and at the same time, test community made rocket league models. where, both processes can run in parallel & locally on my hardware. in the game window — i’m playing against a reinforcement learning ppo model that’s running locally. and in the vscode window — i’m training my own reinforcement learning model (just a dummy example script for now). also, the rocket league botting ecosystem has incredible tooling where you can test out different reinforcement learning ideas against other algorithms + it has great documentation for linux and windows. it’s honestly a beautiful hidden gem of a rabbit hole :)

naklecha

46,795 views • 1 year ago