AIIR-MIX: Multi-Agent Reinforcement Learning Meets Attention Individual Intrinsic Reward Mixing Network

no code implementations • 19 Feb 2023 • Wei Li, Weiyan Liu, Shitong Shao, Shiyi Huang

The results show that AIIR-MIX can dynamically assign each agent a real-time intrinsic reward in accordance with their actual contribution.

Multi-agent Reinforcement Learning Starcraft +1