Multi-agent reinforcement learning based on local communication
Sign Up to like & getrecommendations! Published in 2018 at "Cluster Computing"
DOI: 10.1007/s10586-018-2597-x
Abstract: Aiming at the locality and uncertainty of observations in large-scale multi-agent application scenarios, the model of Decentralized Partially Observable Markov Decision Processes (DEC-POMDP) is considered, and a novel multi-agent reinforcement learning algorithm based on local… read more here.
Keywords: agent; reinforcement learning; multi agent; local communication ... See more keywords