Over the last couple years I've been training a reinforcement learning agent to play pokemon red. I put together a video documenting the AI's learning, and my process creating it. Enjoy!
🔗 youtu.be/DcYLT37ImBY
Peter Whidden
54 posts
- I’m giving a talk on my new project next month!Join us on August 13 for Localhost! 🦠 @computerender will present Mote, an interactive ecosystem simulation with hundreds of thousands of organisms. His custom GPU physics engine models many simple behaviors at a massive scale, producing fascinating emergent phenomena. RSVP⬇️
00:00 - talk is uploaded!🦠Watch @computerender's first public talk on Mote: an interactive ecosystem simulation! Mote uses a custom GPU-based physics engine to model hundreds of thousands of organisms, leading to fascinating emergent phenomena: a sandbox that is part game, part research. Link below⬇️
- New tutorial available showing how to use computerender for vid2vid styling! github.com/computerender/… #stablediffusion #vid2vid
00:00 - Amazing to see how quickly a community is forming around RL for Pokemon. @dvruette and others have been working on support for gen3 games and are already making a ton of progress! More soonBaby steps... AI has previously learned to play Pokemon Red, and now it's learning to play Pokemon Emerald as well. What will be the biggest obstacles on its journey to become a Pokemon master?
00:00 - David's been doing awesome work on this! It's been super fun to see this develop in the last couple years. Check out his blog post!Excited to finally share our progress in developing a reinforcement learning system to beat Pokémon Red. Our system successfully completes the game using a policy under 10M parameters, PPO, and a few novel techniques. Blog posted below
00:00 - Looking forward to this!Peter Whidden @computerender will be presenting his work on playing Pokemon with reinforcement learning at LIFE monthly Monday 11/13 at 9 AM PT / Noon ET. DM me your email for an invitation!
GIF - The work Mykhailo has been doing on this project is incredibly impressive. He's created the first tensor/ml library that supports pytorch nn style code, realtime rendering, and non-nvidia gpus. He's already made a ton of amazing demos. Check out the blog post & star the repo!I wrote a blog post about my own Python tensor compiler library called TensorFrost that I've been working on for the last 14 months! michaelmoroz.github.io/WritingAnOptim… As a sneak peak here is the last pet project that I've made using it - an implementation of Neural Cellular Automata:
00:00 - Can dynamics be distilled from models trained on only static 2D images? An experiment distilling Stable Diffusion into @zzznah's Neural Cellular Automata model using @poolio's method from DreamFusion. Prompt: "raindrops on glass" More info and code: github.com/computerender/…
00:00 - Our site now features a request builder UI that automatically generates code to reproduce the request using curl, js, or python computerender.com/models-sd.html #stablediffusion
00:00 - Replying to @jsuarezThis is awesome! Stoked to see some videos of the trained policies and more future developments. Nice work!
- Replying to @computerenderGiven this, perhaps it is possible that dynamics could be distilled into a model that enforces a consistent structure over time and space. These experiments are a first step in this direction!
- The computerender API is so simple you can test it out right in your browser's URL bar! api.computerender.com/generate/blue-…
GIF
