Metraipolis › archive › dc_b4bcffb5e6ae
Homomorphic Advantage Operator: Stabilizing Reinforcement Learning Under Fully Homomorphic Encryption Constraints — arXiv:2610.02074
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.02074
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:07:02.874Z
- SHA-256 of the archived text
b7c43e512f442183d6b1ac7a28041a1f427f0c30d12a6e62862456bf5e6c5635- Stable URL of this page
https://metraipolis.com/documento/dc_b4bcffb5e6ae
How to cite
Homomorphic Advantage Operator: Stabilizing Reinforcement Learning Under Fully Homomorphic Encryption Constraints — arXiv:2610.02074 — arXiv (en), https://arxiv.org/abs/2610.02074 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b4bcffb5e6ae (Metraipolis archive dc_b4bcffb5e6ae, sha256 b7c43e512f442183d6b1ac7a28041a1f427f0c30d12a6e62862456bf5e6c5635)
BibTeX
@misc{dcb4bcffb5e6ae,
title = {Homomorphic Advantage Operator: Stabilizing Reinforcement Learning Under Fully Homomorphic Encryption Constraints — arXiv:2610.02074},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.02074},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b4bcffb5e6ae; sha256 b7c43e512f442183d6b1ac7a28041a1f427f0c30d12a6e62862456bf5e6c5635},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.02074. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Privacy-preserving machine learning presents significant deployment challenges on the cloud for intelligent systems with confidential data. Fully Homomorphic Encryption (FHE) offers a compelling solution for secure computation, preserving data confidentiality of cloud computations. However, applying FHE to reinforcement learning (RL) requires replacing non-linear operations with polynomial approximations, which diverge catastrophically due to a unique recursive error phenomenon known as the Bellman drift. This article introduces the Homomorphic Advantage Operator (HAO), a stabilization framework designed to prevent polynomial approximation divergence in FHE-based deep RL. HAO adapts the zero-mean centering projection from advantage-based value estimation directly to temporal-difference (TD) targets. This linear projection annihilates the uniform state-value baseline that drives the Bellman drift, maintaining per-state action rankings while requiring zero additional non-linear multiplicative depth and avoiding expensive ciphertext bootstrapping. The proposed HAO framework was evaluated using a three-tier experimental methodology, including a tabular Markov Decision Process (MDP), an encrypted CartPole environment using real CKKS cryptographic operations, and a 20-node logistics routing benchmark with dense continuous features. The results demonstrate that the proposed HAO strictly bounds network pre-activations within the safe polynomial approximation domain. The proposed HAO RL agents achieved 0% boundary breaches across all random seeds used, whereas regularization alone (L2 weight decay and gradient clipping) breached the bound on 3 of 5 seeds and the unstabilized baseline did so in 83.8% of episodes. Finally, HAO agents improve optimal policy accuracy by 18.0 percentage points in tabular domains and remain stable when DP-SGD-style Gaussian noise is added to the clipped gradients. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2610.02074 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T10:21:28.000Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).