Metraipolis › archive › dc_17c772c96e65
Preserving the Privacy of Reward Functions in MDPs through Deception — arXiv:2407.09809
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2407.09809
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T21:52:38.428Z
- SHA-256 of the archived text
c9ce051e231199ef9a5915ee3b73b7a7fdb8b578082076d318493892ed699498- Stable URL of this page
https://metraipolis.com/documento/dc_17c772c96e65
How to cite
Preserving the Privacy of Reward Functions in MDPs through Deception — arXiv:2407.09809 — arXiv (en), https://arxiv.org/abs/2407.09809 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_17c772c96e65 (Metraipolis archive dc_17c772c96e65, sha256 c9ce051e231199ef9a5915ee3b73b7a7fdb8b578082076d318493892ed699498)
BibTeX
@misc{dc17c772c96e65,
title = {Preserving the Privacy of Reward Functions in MDPs through Deception — arXiv:2407.09809},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2407.09809},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_17c772c96e65; sha256 c9ce051e231199ef9a5915ee3b73b7a7fdb8b578082076d318493892ed699498},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2407.09809. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Preserving the privacy of preferences (or rewards) of a sequential decision-making agent when decisions are observable is crucial in many physical and cybersecurity domains. For instance, in wildlife monitoring, agents must allocate patrolling resources without revealing animal locations to poachers. This paper addresses privacy preservation in planning over a sequence of actions in MDPs, where the reward function represents the preference structure to be protected. Observers can use Inverse RL (IRL) to learn these preferences, making this a challenging task. Current research on differential privacy in reward functions fails to ensure guarantee on the minimum expected reward and offers theoretical guarantees that are inadequate against IRL-based observers. To bridge this gap, we propose a novel approach rooted in the theory of deception. Deception includes two models: dissimulation (hiding the truth) and simulation (showing the wrong). Our first contribution theoretically demonstrates significant privacy leaks in existing dissimulation-based methods. Our second contribution is a novel RL-based planning algorithm that uses simulation to effectively address these privacy concerns while ensuring a guarantee on the expected reward. Experiments on multiple benchmark problems show that our approach outperforms previous methods in preserving reward function privacy. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2407.09809 — 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 2026-11-04T21:38:49.774Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).