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

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

An elegant PyTorch offline reinforcement learning library for researchers.

📚 List of Top-tier Conference Papers on Reinforcement Learning (RL)，including: NeurIPS, ICML, AAAI, IJCAI, AAMAS, ICLR, ICRA, etc.

A Japanese (Riichi) Mahjong AI Framework

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 MARL.

Clean single-file implementation of offline RL algorithms in JAX

A simple and easy-to-use autonomous driving environment for reinforcement learning, based on the CARLA simulator.

PyTorch implementation of the Offline Reinforcement Learning algorithm CQL. Includes the versions DQN-CQL and SAC-CQL for discrete and continuous action spaces.

Python interface for accessing the near real-world offline reinforcement learning (NeoRL) benchmark datasets

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"

Unified Implementations of Offline Reinforcement Learning Algorithms

Official PyTorch implementation of "Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble" (NeurIPS'21)

Pytorch Implementation of Stochastic MuZero for gym environment. This algorithm is capable of supporting a wide range of action and observation spaces, including both discrete and continuous variations.

[ICLR 2025] The offical implementation of "PSEC: Skill Expansion and Composition in Parameter Space", a new framework designed to facilitate efficient and flexible skill expansion and composition, iteratively evolve the agents' capabilities and efficiently address new challenges

[NeurIPS 2022 Oral] The official implementation of POR in "A Policy-Guided Imitation Approach for Offline Reinforcement Learning"

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