Privacy-preserving reinforcement learning

Jun Sakuma, Shigenobu Kobayashi, Rebecca N. Wright

Abstract: We consider the problem of distributed reinforcement learning (DRL) from private perceptions. In our setting, agents' perceptions, such as states, rewards, and actions, are not only distributed but also should be kept private. Conventional DRL algorithms can handle multiple agents, but do not necessarily guarantee privacy preservation and may not guarantee optimality. In this work, we design cryptographic solutions that achieve optimal policies without requiring the agents to share their private information.