RL/ML
High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC
🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX
A library of reinforcement learning components and agents
SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners
⚡ Flashbax: Accelerated Replay Buffers in JAX
Mastering Diverse Domains through World Models
A framework for easy prototyping of distributed reinforcement learning algorithms
A collection of reference environments for offline reinforcement learning
A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities
Author's PyTorch implementation of TD7 for online and offline RL
notes for software engineers getting up to speed on new AI developments. Serves as datastore for https://latent.space writing, and product brainstorming, but has cleaned up canonical references und…
Tutorial: Tools for Robotic Reinforcement Learning, Hands-on RL for Robotics with EAGER and Stable-Baselines3
Offline Reinforcement Learning (aka Batch Reinforcement Learning) on Atari 2600 games
An Open Source package that allows video game creators, AI researchers and hobbyists the opportunity to learn complex behaviors for their Non Player Characters or agents
An offline deep reinforcement learning library
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
robomimic: A Modular Framework for Robot Learning from Demonstration
robosuite: A Modular Simulation Framework and Benchmark for Robot Learning
Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary hyperparameter optimization.
An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities
An elegant PyTorch deep reinforcement learning library.
An educational resource to help anyone learn deep reinforcement learning.
Really Fast End-to-End Jax RL Implementations