matd3

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

Projects from basic algorithms to MARL. Implements MADDPG,MATD3,MA/HAPPO in Predator-Prey pursuit games with PettingZoo MPE environments.

Multi-UAV Assisted Wireless Powered Mobile Edge Computing: A hybrid optimization approach of combining multi-agent RL techniques (including attention mechanisms) with collaborative and adaptive caching policies for supporting mobile edge computing through UAVs.

Multi-agent reinforcement learning framework for Unity environments. Implements MAPPO, MASAC, MATD3, and MADDPG with comprehensive evaluation tools. Features sample-efficient training, competitive analysis, and pre-trained models achieving great performance in Tennis and Soccer environments.

Official implementation of "Edge-Driven Multi-Agent Systems for Decentralized Stability in Autonomous Smart Grids." Featuring MATD3 reinforcement learning, 6G-enabled URLLC latency benchmarks, and OpenDSS-G power flow simulations for 35% grid resilience.