$QD$-Learning: A Collaborative Distributed Strategy for Multi-Agent Reinforcement Learning Through Consensus + Innovations

Soummya Kar José M. F. Moura H. Vincent Poor $QD$-Learning: A Collaborative Distributed Strategy for Multi-Agent Reinforcement Learning Through Consensus + Innovations http://arxiv.org/abs/1205.0047 2012 CoRR abs/1205.0047 db/journals/corr/corr1205.html#abs-1205-0047