English

SARSA(0) Reinforcement Learning over Fully Homomorphic Encryption

Systems and Control 2021-01-26 v2 Cryptography and Security Systems and Control

Abstract

We consider a cloud-based control architecture in which the local plants outsource the control synthesis task to the cloud. In particular, we consider a cloud-based reinforcement learning (RL), where updating the value function is outsourced to the cloud. To achieve confidentiality, we implement computations over Fully Homomorphic Encryption (FHE). We use a CKKS encryption scheme and a modified SARSA(0) reinforcement learning to incorporate the encryption-induced delays. We then give a convergence result for the delayed updated rule of SARSA(0) with a blocking mechanism. We finally present a numerical demonstration via implementing on a classical pole-balancing problem.

Cite

@article{arxiv.2002.00506,
  title  = {SARSA(0) Reinforcement Learning over Fully Homomorphic Encryption},
  author = {Jihoon Suh and Takashi Tanaka},
  journal= {arXiv preprint arXiv:2002.00506},
  year   = {2021}
}

Comments

7 pages, 2 figures, submitted to SICE ISCS 2021; replaced with supplementary paragraphs added and format change for the correct publishing medium

R2 v1 2026-06-23T13:28:28.579Z