UneVEn: Universal Value Exploration for
Multi-Agent Reinforcement Learning
Tarun Gupta 1 Anuj Mahajan 1 Bei Peng 1 Wendelin Bohmer 2 Shimon Whiteson 1
Abstract factorization, the joint action value function can be decen-
trally maximized as each agent can simply select the action
VDN and QMIX are two popular value-based
that maximizes its corresponding utility function ...


雷达卡




京公网安备 11010802022788号







