Learning Cooperative Multi-Agent Policies With Partial Reward Decoupling
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Robotics and Automation Letters"
DOI: 10.1109/lra.2021.3135930
Abstract: One of the preeminent obstacles to scaling multi-agent reinforcement learning to large numbers of agents is assigning credit to individual agents’ actions. In this letter, we address this credit assignment problem with an approach that… read more here.
Keywords: partial reward; reward decoupling; multi agent; multi ... See more keywords