Train transformer language models with reinforcement learning.

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

Code of the paper "Universal Morphology Control via Contextual Modulation" at ICML 2023

OpenDILab Decision AI Engine

Decision Intelligence Adventure for Beginners

An elegant PyTorch offline reinforcement learning library for researchers.

rl-papers

A (somewhat) minimal library for finetuning language models with PPO on human feedback.

A modular RL library to fine-tune language models to human preferences

Assignments for Berkeley CS 285: Deep Reinforcement Learning (Fall 2022)

DI-engine docs (Chinese and English)

The MARL extension for RLlib. A benchmark for research and industry.

DrQ-v2: Improved Data-Augmented Reinforcement Learning

Collection of papers and resources for data augmentation (DA) in visual reinforcement learning (RL).

PyTorch implementations of popular off-policy multi-agent reinforcement learning algorithms, including QMix, VDN, MADDPG, and MATD3.

This is the official implementation of Multi-Agent PPO (MAPPO).

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

StarCraft II Client - protocol definitions used to communicate with StarCraft II.

This repo is the official implementation of "Mask-based Latent Reconstruction for Reinforcement Learning" (NeurIPS 2022).

Fine-tuned MARL algorithms on SMAC (100% win rates on most scenarios)

Mobile App Tasks with Iterative Feedback (MoTIF): Addressing Task Feasibility in Interactive Visual Environments