PooL: Pheromone-inspired Communication Framework forLarge Scale Multi-Agent Reinforcement Learning

no code implementations • 20 Feb 2022 • Zixuan Cao, Mengzhi Shi, Zhanbo Zhao, Xiujun Ma

Pheromones released by agents of PooL are defined as outputs of most reinforcement learning algorithms, which reflect agents' views of the current environment.

Multi-agent Reinforcement Learning Q-Learning +2