Metraipolis › archive › dc_d8d044adb210

Recommender regret for improving regularised RL estimation with bandits and MCTS — arXiv:2610.32910

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.32910
License (as archived)
CC0-1.0
Archived
2026-10-26T20:13:28.351Z
SHA-256 of the archived text
e5d89db5a6cfc0c591bd0899161d0cc2381a1f4a4bcbded8e78e1cfc8b777401
Stable URL of this page
https://metraipolis.com/documento/dc_d8d044adb210

How to cite

Recommender regret for improving regularised RL estimation with bandits and MCTS — arXiv:2610.32910 — arXiv (en), https://arxiv.org/abs/2610.32910 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d8d044adb210 (Metraipolis archive dc_d8d044adb210, sha256 e5d89db5a6cfc0c591bd0899161d0cc2381a1f4a4bcbded8e78e1cfc8b777401)
BibTeX
@misc{dcd8d044adb210,
  title = {Recommender regret for improving regularised RL estimation with bandits and MCTS — arXiv:2610.32910},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.32910},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d8d044adb210; sha256 e5d89db5a6cfc0c591bd0899161d0cc2381a1f4a4bcbded8e78e1cfc8b777401},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32910. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Regularised reinforcement learning (RL) algorithms rely on estimators, like Monte Carlo tree search or one-step look-ahead, to provide policy, value, or Q-value estimates in training and inference. However, existing bandit-based estimation frameworks evaluate sampling efficiency, not the quality of estimates. We address this by formalising estimate generation as a recommendation process, treating bandit-based sampling as an improvement operator. To evaluate the quality of a recommendation (estimate), we define regulariser-aware recommender regrets, analysing their lower bounds, and proving that simple algorithms like uniform sampling can achieve these bounds. Finally, we unify bandit- and search-based target improvement under recommender MCTS. Across synthetic trees, arcade games, and scientific discovery tasks, recommenders often yield faster target convergence and superior downstream performance. Our experiments characterise for the first time the potential of regularised MCTS in scientific applications.

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/2610.32910 — 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 2026-10-26T19:49:03.439Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).