Relative Entropy Regularized Reinforcement Learning for Efficient Encrypted Policy Synthesis
Year: 2025
Type: article
Abstract: We propose an efficient encrypted policy synthesis to develop privacy-preserving model-based reinforcement learning. We first demonstrate that the relative-entropy-regularized reinforcement learning framework offers a computationally convenient linear and “min-free” structure for value iteration, enabling a direct and efficient integration of fully homomorphic encryption with bootstrapping into policy synthesis. Convergence and error bounds are analyzed as encrypted policy synthesis propagates errors under the presence of encryption-induced errors including quantization and bootstrapping. Theoretical analysis is validated by numerical simulations. Results demonstrate the effectiveness of the RERL framework in integrating FHE for encrypted policy synthesis.
Source: IEEE Control Systems Letters
Authors: Jihoon Suh, Yeongjun Jang, Kaoru Teranishi, Takashi Tanaka
Institutions: Purdue University West Lafayette, Seoul National University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4411203209