PufferAI / PufferLibLinks
Simplifying reinforcement learning for complex game environments
☆4,954Updated this week
Alternatives and similar repositories for PufferLib
Users that are interested in PufferLib are comparing it to the libraries listed below
Sorting:
- Our library for RL environments + evals☆3,791Updated this week
- NanoGPT (124M) in 2 minutes☆4,515Updated last week
- Thermodynamic Hypergraphical Model Library in JAX☆998Updated 2 months ago
- Can you design a controller to steer a simulated car?☆342Updated 6 months ago
- Tutorials on tinygrad☆455Updated 3 months ago
- (WIP) A small but powerful, homemade PyTorch from scratch.☆672Updated last week
- If tinygrad wasn't small enough for you...☆774Updated last year
- Implementing DeepSeek R1's GRPO algorithm from scratch☆1,759Updated 9 months ago
- The Fastest Deep Reinforcement Learning Library☆924Updated 2 weeks ago
- Mastering Diverse Domains through World Models☆2,758Updated 4 months ago
- From the Tensor to Stable Diffusion, a rough outline for a 1 week course.☆1,074Updated 4 months ago
- Really Fast End-to-End Jax RL Implementations☆1,017Updated last year
- Distributed Training Over-The-Internet☆975Updated 3 months ago
- Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary h…☆869Updated last week
- [NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards☆1,326Updated 3 weeks ago
- PyTorch implementations of algorithms from "Reinforcement Learning: An Introduction by Sutton and Barto", along with various RL research …☆205Updated 5 months ago
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,860Updated 7 months ago
- Frontier Models playing the board game Diplomacy.☆627Updated last month
- Entropy Based Sampling and Parallel CoT Decoding☆3,436Updated last year
- LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.☆669Updated 5 months ago
- A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.☆3,292Updated this week
- Continuous Thought Machines, because thought takes time and reasoning is a process.☆1,750Updated last month
- Deep learning for dummies. All the practical details and useful utilities that go into working with real models.☆829Updated 6 months ago
- Monte Carlo tree search in JAX☆2,587Updated 5 months ago
- Solve puzzles to improve your tinygrad skills!☆178Updated 3 months ago
- Distributed Reinforcement Learning accelerated by Lightning Fabric☆422Updated last week
- Massively parallel rigidbody physics simulation on accelerator hardware.☆3,046Updated last week
- A non-saturating, open-ended environment for evaluating LLMs in Factorio☆903Updated last month
- UNet diffusion model in pure CUDA☆661Updated last year
- High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, T…☆9,046Updated 6 months ago