d4rl topic

A collection of robotics simulation environments for reinforcement learning

Farama-Foundation

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

Howuhh

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

tinkoff-ai

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

thu-ml

Clean single-file implementation of offline RL algorithms in JAX

nissymori