当前位置:
X-MOL 学术
›
arXiv.cs.MA
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Calibration of Shared Equilibria in General Sum Partially Observable Markov Games
arXiv - CS - Multiagent Systems Pub Date : 2020-06-23 , DOI: arxiv-2006.13085 Nelson Vadori and Sumitra Ganesh and Prashant Reddy and Manuela Veloso
arXiv - CS - Multiagent Systems Pub Date : 2020-06-23 , DOI: arxiv-2006.13085 Nelson Vadori and Sumitra Ganesh and Prashant Reddy and Manuela Veloso
Training multi-agent systems (MAS) to achieve realistic equilibria gives us a
useful tool to understand and model real-world systems. We consider a general
sum partially observable Markov game where agents of different types share a
single policy network, conditioned on agent-specific information. This paper
aims at i) formally understanding equilibria reached by such agents, and ii)
matching emergent phenomena of such equilibria to real-world targets. Parameter
sharing with decentralized execution has been introduced as an efficient way to
train multiple agents using a single policy network. However, the nature of
resulting equilibria reached by such agents has not been yet studied: we
introduce the novel concept of Shared equilibrium as a symmetric pure Nash
equilibrium of a certain Functional Form Game (FFG) and prove convergence to
the latter for a certain class of games using self-play. In addition, it is
important that such equilibria satisfy certain constraints so that MAS are
calibrated to real world data for practical use: we solve this problem by
introducing a novel dual-Reinforcement Learning based approach that fits
emergent behaviors of agents in a Shared equilibrium to externally-specified
targets, and apply our methods to a n-player market example. We do so by
calibrating parameters governing distributions of agent types rather than
individual agents, which allows both behavior differentiation among agents and
coherent scaling of the shared policy network to multiple agents.
更新日期:2020-10-26