mappo-competitive-reinforcement

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

Concise pytorch implements of MARL algorithms, including MAPPO, MADDPG, MATD3, QMIX and VDN.

Multi-agent PPO with noise (97% win rates on Hard scenarios of SMAC)

General-Purpose Reinforcement Learning

RLToolkit is a flexible and high-efficient reinforcement learning framework. Include implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....

Potentially helpful methods for specialized ensemble learning.