Metraipolis › archive › dc_4df3fe5e9039
Square-Root Regret for Adversarial Multiplayer Bandits without Collision Information or Shared Randomness — arXiv:2610.05688
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.05688
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:24:02.595Z
- SHA-256 of the archived text
81ff422a2ea888b848e1ae23ab0b021e68e7efcec672ae9700567b66fc06ed34- Stable URL of this page
https://metraipolis.com/documento/dc_4df3fe5e9039
How to cite
Square-Root Regret for Adversarial Multiplayer Bandits without Collision Information or Shared Randomness — arXiv:2610.05688 — arXiv, https://arxiv.org/abs/2610.05688 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4df3fe5e9039 (Metraipolis archive dc_4df3fe5e9039, sha256 81ff422a2ea888b848e1ae23ab0b021e68e7efcec672ae9700567b66fc06ed34)
BibTeX
@misc{dc4df3fe5e9039,
title = {Square-Root Regret for Adversarial Multiplayer Bandits without Collision Information or Shared Randomness — arXiv:2610.05688},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.05688},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4df3fe5e9039; sha256 81ff422a2ea888b848e1ae23ab0b021e68e7efcec672ae9700567b66fc06ed34},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05688. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study adversarial multiplayer bandits with $K$ arms and $2\le m<K$ labeled players, without collision information, shared randomness, or an external communication channel. We design a constructive communication and synchronization protocol with a Monte Carlo public constructor. With probability at least $1-CN^{-32}$ over preprocessing, where $N=2Km(T+1)$, its fixed published output satisfies \[ R_T\le C K^{5/2}\sqrt T\log^2(2Km(T+1)) \] simultaneously for every oblivious reward sequence chosen after preprocessing. Here $R_T$ is expected regret over the players' private execution randomness. Positive reward observations establish a common learning schedule and synchronize players before learning begins. The cost of delayed communication is charged to the support of positive rewards, ensuring that periods with little useful feedback incur only limited regret. A slow--fast learning procedure then maintains valid reward estimates while assignments and scores are exchanged.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.05688 — 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 2026-10-06T05:23:50.235Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).