Survey of recent multi-agent reinforcement learning algorithms utilizing centralized training
Piyush K. Sharma, Erin G. Zaroukian, Rolando Fernandez, Anjon Basak, Derrik E. Asher
Abstract
Much work has been dedicated to the exploration of Multi-Agent Reinforcement Learning (MARL) paradigms implementing a centralized learning with decentralized execution approach to improve human-like collaboration in cooperative tasks. Here, we introduce variations of centralized training to describe cases where shared/independent reward structure is utilized to improve learning by training agents in an intelligent way, and to analyze cooperative behavior in multi-agent systems. This work discusses implications for providing a classification of the recent MARL algorithmic approaches on the basis of their information sharing mechanism (e.g., reward, gradient, action, parameter, observation/state space sharing) on cooperative behavior in multi-agent systems.