Popular GitHub Repositories for Offline Reinforcement Learning

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

An elegant PyTorch offline reinforcement learning library for researchers.

Minimal implementation of Decision Transformer: Reinforcement Learning via Sequence Modeling in PyTorch for mujoco control tasks in OpenAI gym

A collection of offline reinforcement learning algorithms.

Datasets with baselines for offline multi-agent reinforcement learning.

Clean single-file implementation of offline RL algorithms in JAX

Code release for Efficient Planning in a Compact Latent Action Space (ICLR2023) https://arxiv.org/abs/2208.10291.

[ICLR 2024] The official implementation of "Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model"

Official implementation for "Anti-Exploration by Random Network Distillation", ICML 2023

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

Official implementation of "Direct Preference-based Policy Optimization without Reward Modeling" (NeurIPS 2023)

[ICML 2022] The official implementation of DWBC in "Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations"

[NeurIPS 2023] The official implementation of "Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization"

Code for NeurIPS 2022 paper Exploiting Reward Shifting in Value-Based Deep RL

Codes for "Efficient Offline Policy Optimization with a Learned Model", ICLR2023

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

[COG24] - Official repository of "OfflineMania: A Benchmark Environment for Offline Reinforcement Learning in Racing Games"

[NeurIPS 2024] PyTorch code for the paper "Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning"

Official implementation for "Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows", NeurIPS 2022, Offline RL Workshop

The First Open-Sourced Building Batch Reinforcement Learning Dataset