# SARSA(0) Reinforcement Learning over Fully Homomorphic Encryption

arXiv: https://arxiv.org/abs/2002.00506 · HTML: https://mlsanity.com/paper/2002.00506/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Feb 2020.

## Built on by (most cited first, 3 of 3)

- [PP-MARL: Efficient Privacy-Preserving Multi-Agent Reinforcement Learning for Cooperative Intelligence in Communications](https://mlsanity.com/paper/2204.12064/) (2022)
- [Efficient Implementation of Reinforcement Learning over Homomorphic Encryption](https://mlsanity.com/paper/2504.09335/) (2025)
- [Relative Entropy Regularized Reinforcement Learning for Efficient Encrypted Policy Synthesis](https://mlsanity.com/paper/2506.12358/) (2025)

## 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.