Metraipolis › archive › dc_55ffae57a49d
Robust Federated Q-Learning with Almost No Communication — arXiv:2609.20174
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.20174
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T04:08:54.974Z
- SHA-256 of the archived text
237d8b4b5cb25de3ca85cb84fd2aa459ced4c818562af014fe936d32fc9e9219- Stable URL of this page
https://metraipolis.com/documento/dc_55ffae57a49d
How to cite
Robust Federated Q-Learning with Almost No Communication — arXiv:2609.20174 — arXiv (en), https://arxiv.org/abs/2609.20174 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_55ffae57a49d (Metraipolis archive dc_55ffae57a49d, sha256 237d8b4b5cb25de3ca85cb84fd2aa459ced4c818562af014fe936d32fc9e9219)
BibTeX
@misc{dc55ffae57a49d,
title = {Robust Federated Q-Learning with Almost No Communication — arXiv:2609.20174},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.20174},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_55ffae57a49d; sha256 237d8b4b5cb25de3ca85cb84fd2aa459ced4c818562af014fe936d32fc9e9219},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20174. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We consider a federated reinforcement learning setting involving $M$ agents, all of whom interact with a common Markov Decision Process (MDP). The agents exchange information via a central server to learn the optimal value function. Our goal is to understand to what extent one can hope for collaborative sample-complexity speedups in such a setting, when a small fraction of the agents are adversarial and can act arbitrarily. To that end, we propose Robust Fed-Q}, a federated Q-learning algorithm that blends ideas from both model-based and model-free RL, along with the median-of-means device from robust statistics. We prove that despite corruption, with high-probability, Robust Fed-Q (i) guarantees exact convergence to the optimal value function in the limit of infinite samples, and (ii) enjoys near-optimal finite-time rates that benefit from collaboration. In addition, our approach requires just $\tilde{O}(1)$ rounds of communication to achieve each of the above guarantees, a feature of independent interest in FL where communication is the major bottleneck.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2609.20174 — 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 2026-10-10T03:48:18.330Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).