General sum stochastic games with networked information flow

Sarah Li, Lillian J Ratliff, Peeyush Kumar

Keywords: stochastic games, multi-agent reinforcement learning, supply chains, actor-critic

TL;DR: As inspired by operation management scenarios such as supply chains, we formulate and empirically analyze a stochastic game model with networked asymmetric information.

Abstract: Inspired by applications such as supply chain management, epidemics, and social networks, we formulate a stochastic game model that addresses three key features common across these domains: 1) network-structured player interactions, 2) pair-wise mixed cooperation and competition among players, and 3) limited global information toward individual decision-making. In combination, these features pose significant challenges for black box approaches taken by deep learning-based multi-agent reinforcement learning (MARL) algorithms and deserve more detailed analysis. We formulate a networked stochastic game with pair-wise general sum objectives and asymmetrical information structure, and empirically explore the effects of information availability on the outcomes of different MARL paradigms such as individual learning and centralized learning decentralized execution. We conclude with a two player supply chain to benchmark existing MARL algorithms and contextualize the challenges at hand.