offline-rl 开源项目推荐（134 个）

opendilab /DI-engine

OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.

Farama-Foundation /Minari

A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities

takuseno /d3rlpy

An offline deep reinforcement learning library

hanjuku-kaso /awesome-offline-rl

An index of algorithms for offline reinforcement learning (offline-rl)

mbreuss /diffusion-literature-for-robotics

关于扩散模型的关键论文和博客总结，帮助你了解该主题。所有已发表的扩散机器人论文详细列表。

yingchengyang /Reinforcement-Learning-Papers

Related papers for reinforcement learning, including classic papers and latest papers in top conferences

opendilab /DI-engine-docs

DI-engine docs (Chinese and English)

Cryolite /kanachan

A Japanese (Riichi) Mahjong AI Framework

liuzuxin /OSRL

🤖 Elegant implementations of offline safe RL algorithms in PyTorch

lubludrova /rl-handbook

A comprehensive guide to Reinforcement Learning

opendilab /GenerativeRL

Python library for solving reinforcement learning (RL) problems using generative models (e.g. Diffusion Models).

Sea-Snell /Implicit-Language-Q-Learning

Official code from the paper "Offline RL for Natural Language Generation with Implicit Language Q Learning"

nissymori /JAX-CORL

Clean single-file implementation of offline RL algorithms in JAX

hakuhodo-technologies /scope-rl

SCOPE-RL: A python library for offline reinforcement learning, off-policy evaluation, and selection

liuzuxin /DSRL

🔥 Datasets and env wrappers for offline safe reinforcement learning

denisyarats /exorl

ExORL: Exploratory Data for Offline Reinforcement Learning

Shanghai-Digital-Brain-Laboratory /BDM-DB1

A large-scale multi-modal pre-trained model

nakamotoo /Cal-QL

official implementation for our paper Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning (NeurIPS 2023)

takuseno /minerva

An out-of-the-box GUI tool for offline deep reinforcement learning

callmespring /RL-short-course

Reinforcement Learning Short Course