Train transformer language models with reinforcement learning.

This is a repository containing the implementation of the One Night Ultimate Werewolf game environment, and an RL-instructed LLM-based agent framework.

A benchmark of test scenarios for multi-agent reinforcement learning.

This repository is an implementation of "MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer" accepted to ICML 2022.

AAGPT is another experimental open-source application showcasing the capabilities of large language models, such as GPT-3.5 and GPT-4.

⚡ Dynamically generated stats for your github readmes

Multi-Agent Constrained Policy Optimisation (MACPO)

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

Safe Multi-Agent MuJoCo benchmark for safe multi-agent reinforcement learning research.

This is the official implementation of Multi-Agent PPO.

Tools for accelerating safe exploration research.

README文件语法解读，即Github Flavored Markdown语法介绍