d4rl

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 collection of robotics simulation environments for reinforcement learning

Clean single-file implementation of offline RL algorithms in JAX

Unified Implementations of Offline Reinforcement Learning Algorithms

Single-file SAC-N implementation on jax with flax and equinox. 10x faster than pytorch

Codes accompanying the paper "Score Regularized Policy Optimization through Diffusion Behavior" (ICLR 2024).

PyTorch Implementation of Offline Reinforcement Learning algorithms

Non-modular implementation of common RL algorithms

Learning from Sparse Offline Datasets via Conservative Density Estimation (ICLR 2024)

a clear and fast jax/flax version of [Diffusion-Policies-for-Offline-RL](https://github.com/Zhendong-Wang/Diffusion-Policies-for-Offline-RL)