MARL @ SJTU

malib

A parallel framework for population-based multi-agent reinforcement learning.

bd_rd_psro

Code for Towards Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum Games

seed_rl

SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.

GTML22_baseline

SJTU course AI3617

RLApps

RLlib-based general reinforcement learning algorithm collections

Competition_Olympics-Running

Olympics-Running Env based on Jidi

dm_control

DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

multiagent-particle-envs

Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

ZSC-Eval