Metraipolis › archive › dc_042a897a482d

Multiagent Evaluation under Incomplete Information — arXiv:1909.09849

Source
arXiv (en)
Original
https://arxiv.org/abs/1909.09849
License (as archived)
CC0-1.0
Archived
2026-10-06T09:31:52.818Z
SHA-256 of the archived text
f2c7fa5f26ce1cf9e8e527992d567ed84bc40a8238f58d505c717ce97ca6333d
Stable URL of this page
https://metraipolis.com/documento/dc_042a897a482d

How to cite

Multiagent Evaluation under Incomplete Information — arXiv:1909.09849 — arXiv (en), https://arxiv.org/abs/1909.09849 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_042a897a482d (Metraipolis archive dc_042a897a482d, sha256 f2c7fa5f26ce1cf9e8e527992d567ed84bc40a8238f58d505c717ce97ca6333d)
BibTeX
@misc{dc042a897a482d,
  title = {Multiagent Evaluation under Incomplete Information — arXiv:1909.09849},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/1909.09849},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_042a897a482d; sha256 f2c7fa5f26ce1cf9e8e527992d567ed84bc40a8238f58d505c717ce97ca6333d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/1909.09849. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper investigates the evaluation of learned multiagent strategies in the incomplete information setting, which plays a critical role in ranking and training of agents. Traditionally, researchers have relied on Elo ratings for this purpose, with recent works also using methods based on Nash equilibria. Unfortunately, Elo is unable to handle intransitive agent interactions, and other techniques are restricted to zero-sum, two-player settings or are limited by the fact that the Nash equilibrium is intractable to compute. Recently, a ranking method called {\alpha}-Rank, relying on a new graph-based game-theoretic solution concept, was shown to tractably apply to general games. However, evaluations based on Elo or {\alpha}-Rank typically assume noise-free game outcomes, despite the data often being collected from noisy simulations, making this assumption unrealistic in practice. This paper investigates multiagent evaluation in the incomplete information regime, involving general-sum many-player games with noisy outcomes. We derive sample complexity guarantees required to confidently rank agents in this setting. We propose adaptive algorithms for accurate ranking, provide correctness and sample complexity guarantees, then introduce a means of connecting uncertainties in noisy match outcomes to uncertainties in rankings. We evaluate the performance of these approaches in several domains, including Bernoulli games, a soccer meta-game, and Kuhn poker.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.ML, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/1909.09849 — 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 2026-10-06T08:24:13.938Z dalla pagina https://arxiv.org/list/stat.ML/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).