A Unified Approach to Dynamic Decision Problems With Asymmetric Information: Nonstrategic Agents

• 成果类型: Article
• 署名作者: Tavafoghi, Hamidreza; Ouyang, Yi; Teneketzis, Demosthenis
• 署名单位: University of California System; University of California Berkeley; University of Michigan System; University of Michigan
• 刊物名称: IEEE TRANSACTIONS ON AUTOMATIC CONTROL
• ISSN/ISSBN: 0018-9286
• DOI: 10.1109/TAC.2021.3060835
• 发表日期: 2022
• 页码: 1105-1119
• 关键词: Asymmetric information; decision making; dynamic programming; multiagent systems; Stochastic systems

摘要

We study a general class of dynamic multi- agent decision problems with asymmetric information and nonstrategic agents, which include dynamic teams as a special case. When agents are nonstrategic, an agent's strategy is known to the other agents. Nevertheless, the agents' strategy choices and beliefs are interdependent over times, a phenomenon known as signaling. We introduce the notion of sufficient information that effectively compresses the agents' information in a mutually consistent manner. Based on the notion of sufficient information, we propose an information state for each agent that is sufficient for decision-making purposes. We present instances of dynamic multiagent decision problems where we can determine an information state with a time-invariant domain for each agent. Furthermore, we present a generalization of the policy-independence property of belief in partially observed Markov decision processes (POMDP) to dynamic multiagent decision problems. Within the context of dynamic teams with asymmetric information, the proposed set of information states leads to a sequential decomposition that decouples the interdependence between the agents' strategies and beliefs over time and enables us to formulate a dynamic program to determine a globally optimal policy via backward induction.