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

An offline deep reinforcement learning library

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

A Japanese (Riichi) Mahjong AI Framework

DI-engine docs (Chinese and English)

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

🤖 Elegant implementations of offline safe RL algorithms in PyTorch

Clean single-file implementation of offline RL algorithms in JAX

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

A large-scale multi-modal pre-trained model

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

ExORL: Exploratory Data for Offline Reinforcement Learning

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

🔥 Datasets and env wrappers for offline safe reinforcement learning

Extreme Q-Learning: Max Entropy RL without Entropy

Benchmarked implementations of Offline RL Algorithms.

Conservative Q learning in Jax

code for paper Query-Dependent Prompt Evaluation and Optimization with Offline Inverse Reinforcement Learning

PyTorch implementation of the implicit Q-learning algorithm (IQL)

Model-based Offline Policy Optimization re-implement all by pytorch