SARSA(0) Reinforcement Learning over Fully Homomorphic Encryption
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 Feb 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 2.
3 papers.
- 2022PP-MARL: Efficient Privacy-Preserving Multi-Agent Reinforcement Learning for Cooperative Intelligence in Communicationscited by 3
- 2025Efficient Implementation of Reinforcement Learning over Homomorphic Encryptioncited by 0
- 2025Relative Entropy Regularized Reinforcement Learning for Efficient Encrypted Policy Synthesiscited by 0
- 2025Relative Entropy Regularized Reinforcement Learning for Efficient Encrypted Policy Synthesis14 Jun 2025
- 2025Efficient Implementation of Reinforcement Learning over Homomorphic Encryption12 Apr 2025
- 2022PP-MARL: Efficient Privacy-Preserving Multi-Agent Reinforcement Learning for Cooperative Intelligence in Communications26 Apr 2022