Deep reinforcement learning based intelligent decision making for multi-player sequential game with uncertain irrational players (Conference Presentation)
Zejian Zhou, Hao Xu · 2020
In this paper, multi-player sequential game with an unknown non-stationary irrational player is investigated for cooperative autonomous robots decision-making applications. In practice, the irrationality of agents can seriously degrade the effectiveness of decision making especially for distributed cooperative tasks with applications to multi-robot systems. Specifically, The irrationality can be caused by the cooperation agent's mechanical failure or sensor flaw. To handle this issue, a novel dynamic evaluation system, which includes two important parameters, i.e. cooperation index and competitive flag, is designed to efficiently quantify the player's level of cooperation or competition firstly. Then, the continuous deep Q network space is proposed to predict the action value with respect to a continuous cooperation index.