Differential Privacy in Cooperative Multiagent PlanningDownload PDF

Published: 08 May 2023, Last Modified: 26 Jun 2023UAI 2023Readers: Everyone
Keywords: differential privacy, multiagent planning, multiagent systems, information theory
TL;DR: We develop a framework to provide inter-agent privacy in multiagent systems and to synthesize policies that remain performant under private communications.
Abstract: Privacy-aware multiagent systems must protect agents' sensitive data while simultaneously ensuring that agents accomplish their shared objectives. Towards this goal, we propose a framework to privatize inter-agent communications in cooperative multiagent decision-making problems. We study sequential decision-making problems formulated as cooperative Markov games with reach-avoid objectives. We apply a differential privacy mechanism to privatize agents' communicated symbolic state trajectories, and analyze tradeoffs between the strength of privacy and the team's performance. For a given level of privacy, this tradeoff is shown to depend critically upon the total correlation among agents' state-action processes. We synthesize policies that are robust to privacy by reducing the value of the total correlation. Numerical experiments demonstrate that the team's performance under these policies decreases by only 6 percent when comparing private versus non-private implementations of communication. By contrast, the team's performance decreases by 88 percent when using baseline policies that ignore total correlation and only optimize team performance.
Supplementary Material: pdf
Other Supplementary Material: zip
0 Replies