thu-rllab

CAMA

Code for ICML2023 accepted paper: Complementary Attention for Multi-Agent Reinforcement Learning.

CFCQL

Code for NeurIPS2023 accepted paper: Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning.

football

Google Research Football

LESR

LLM-Empowered State Representation for Reinforcement Learning (ICML2024 Accepted paper)

pysc2

Based on pysc2==4.0.0, update to disable the logging.

serverusage.github.io

smac

SMAC: The StarCraft Multi-Agent Challenge with a fixed certain version and disabled sc2 logging.

SOG

Code for NeurIPS paper "Self-Organized Group for Cooperative Multi-agentReinforcement Learning".

SPD

Source code for "SPD: Synergy Pattern Diversifying Oriented Unsupervised Multi-agent Reinforcement Learning" (NeurIPS 2022).

zsh-configuration

Install ZSH to free your shell.

thu-rllab/CFCQL

Code for NeurIPS2023 accepted paper: Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning.

thu-rllab/SOG

Code for NeurIPS paper "Self-Organized Group for Cooperative Multi-agentReinforcement Learning".

thu-rllab/LESR

LLM-Empowered State Representation for Reinforcement Learning (ICML2024 Accepted paper)

thu-rllab/CAMA

Code for ICML2023 accepted paper: Complementary Attention for Multi-Agent Reinforcement Learning.

thu-rllab/SPD

Source code for "SPD: Synergy Pattern Diversifying Oriented Unsupervised Multi-agent Reinforcement Learning" (NeurIPS 2022).

thu-rllab/zsh-configuration

Install ZSH to free your shell.

thu-rllab/football

Google Research Football

thu-rllab/pysc2

Based on pysc2==4.0.0, update to disable the logging.

thu-rllab/rtd_marl_docs

thu-rllab/serverusage.github.io

thu-rllab/smac

SMAC: The StarCraft Multi-Agent Challenge with a fixed certain version and disabled sc2 logging.

thu-rllab/smacv2