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

Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

Repo for Implicit Diffusion Q-Learning

JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.

A DDPM implementation in Jax for continuous space modeling.

Official Jax implementation of AlignIQL.

Generalized Decision Transformer for Offline Hindsight Information Matching (ICLR2022)

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

[ICLR 2023 Oral] The official implementation of SQL and EQL in "Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization"

Author's implementation of ReBRAC, a minimalist improvement upon TD3+BC

Official implementation for "Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size", NeurIPS 2022, Offline RL Workshop

Implementation of Decision Transformer, Conservative Q-Learning, and Behavior Cloning in Offline Reinforcement Learning setting

An offline deep reinforcement learning library