Metraipolis › archive › dc_0972bb29ce99

Strategic Multi-Agent Learning for Interpretable Action Valuation of All Players in Football — arXiv:2610.05961

Source: arXiv
Original: https://arxiv.org/abs/2610.05961
License (as archived): CC0-1.0
Archived: 2026-10-06T05:31:22.755Z
SHA-256 of the archived text: d571bde5171031594423a0414e948471de056b59cb95a5d71b39a0933de51bca
Stable URL of this page: https://metraipolis.com/documento/dc_0972bb29ce99

How to cite

Strategic Multi-Agent Learning for Interpretable Action Valuation of All Players in Football — arXiv:2610.05961 — arXiv, https://arxiv.org/abs/2610.05961 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0972bb29ce99 (Metraipolis archive dc_0972bb29ce99, sha256 d571bde5171031594423a0414e948471de056b59cb95a5d71b39a0933de51bca)

BibTeX

@misc{dc0972bb29ce99,
  title = {Strategic Multi-Agent Learning for Interpretable Action Valuation of All Players in Football — arXiv:2610.05961},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05961},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0972bb29ce99; sha256 d571bde5171031594423a0414e948471de056b59cb95a5d71b39a0933de51bca},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05961. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Valuing player actions in football requires accounting for strategic interactions among 22 players, including off-ball movements and defensive positioning. Existing reinforcement-learning-based methods commonly aggregate decisions at the team level or estimate player values independently, leaving strategic interdependence among players insufficiently represented. This study proposes an action valuation framework inspired by Markov perfect equilibrium (MPE) for all players. Each possession is modeled as a finite-horizon dynamic game, with each player represented as an autonomous agent whose policy depends on the current game state. MPE is used as a motivating solution concept rather than an exact equilibrium. To improve interpretability, we use Expandable Decision-Making States (EDMS) and decompose the Q-value into a successor-feature basis and a linear reward-weight vector. The value basis is estimated by linear TD initialization followed by nonlinear refinement. Using tracking and event data from 95 J1 League matches, we compare the proposed formulation with an independent reinforcement learning baseline. Because the two formulations define TD errors in different target spaces, TD MSE is used only for within-formulation consistency. With EDMS fixed, the independent baseline assigns the highest value to forward movement in 99.21% of evaluated off-ball states, whereas the most frequent direction under the proposed formulation accounts for 17.63%. Team-level average Q-values show a negative association with season-level expected goals for the baseline and a weakly positive association for the proposed formulation. Qualitative analyses illustrate context-dependent valuations of off-ball movements and defensive positioning. Overall, the proposed formulation produces more context-sensitive action rankings, although the comparison does not isolate the MPE-inspired component.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.05961 — 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 2026-10-06T05:27:05.844Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).