General sum stochastic games with networked information flows
This work addresses challenges in multi-agent systems for applications such as supply chain management and social networks, but it appears incremental as it builds on existing MARL paradigms without introducing a fundamentally new approach.
The paper tackled the problem of modeling stochastic games with networked interactions, mixed cooperation-competition, and limited information, common in domains like supply chains and epidemics, by formulating a networked stochastic game and empirically exploring how information availability affects multi-agent reinforcement learning outcomes.
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.