AI/ML●●Solid
REST API for Gymnasium (fka OpenAI Gym) reinforcement learning library
Revives deprecated OpenAI gym-http-api with Docker images and built-in browser monitoring views.
Niche GemShip It
cloudkj
112mo ago
Back to browse
Run RL agents in the browser with WebGPU
by umjunsik132·May 26, 2026·3 points·1 comment
AI Analysis
●●●BangerWizardryCrowd Pleaser
WebGPU-powered RL training in browser—no install, no cloud, just train.
Strengths
- •WebGPU hardware acceleration enables local RL training without cloud dependencies.
- •Battle arena variants like MountainCarBattle add competitive learning angles.
- •Community leaderboard system creates engagement beyond solo experimentation.
Weaknesses
- •Limited environment selection compared to established RL libraries like Gymnasium.
- •No visible model export options for deploying trained agents elsewhere.
Category
Target Audience
ML engineers, students learning reinforcement learning, AI educators
Similar To
Gymnasium · RLlib · Neural Network Playground
Similar Projects
AI/ML●Mid
Neural Siege – A Multi-Agent RL Combat Simulation
Vectorized multi-agent RL combat sim with deterministic checkpointing and telemetry logging.
Big BrainWizardry
luthor190397
203mo ago
AI/ML●●Solid
PPO agent reduces elevator wait times by 84% vs. classical dispatching
PPO beats classical elevator dispatch 6x on wait times; niche but rigorous.
Big BrainRabbit Hole
jonas-is-coding
203mo ago
AI/ML●●●Banger
Autoresearch-WebGPU uses agents to iteratively train LMs in the browser
Runs autoresearch agents entirely in-browser using WebGPU and jax-js.
WizardryBig Brain
lucasgelfond
103mo ago
AI/ML●●Solid
A 178K Neural Net that beats Pokémon Roguelike
178K neural net beats Pokémon roguelike with clever 1386-dim state encoding.
Rabbit HoleNiche GemCozy
farcaster
306d ago
AI/ML●●●Banger
Watch a neural net learn to play Snake
Runs PPO training entirely in-browser via TinyJit WebGPU kernels.
WizardryRabbit Hole
c1b
205471mo ago