Differentially Private Reinforcement Learning with Self-Play

arXiv:2404.07559v1 Announce Type: new
Abstract: We study the problem of multi-agent reinforcement learning (multi-agent RL) with differential privacy (DP) constraints. This is well-motivated by various real-world applications involving sensitive data, where it is critical to protect users' private information. We first extend the definitions of Joint DP (JDP) and Local DP (LDP) to two-player zero-sum episodic Markov Games, where both definitions ensure trajectory-wise privacy protection. Then we design a provably efficient algorithm based on optimistic Nash value iteration and privatization …

abstract agent applications arxiv constraints cs.ai cs.cr cs.lg cs.ma data definitions differential differential privacy information multi-agent privacy protect reinforcement reinforcement learning self-play stat.ml study type world