English

Stabilized Nested Rollout Policy Adaptation

Artificial Intelligence 2021-01-12 v1

Abstract

Nested Rollout Policy Adaptation (NRPA) is a Monte Carlo search algorithm for single player games. In this paper we propose to modify NRPA in order to improve the stability of the algorithm. Experiments show it improves the algorithm for different application domains: SameGame, Traveling Salesman with Time Windows and Expression Discovery.

Keywords

Cite

@article{arxiv.2101.03563,
  title  = {Stabilized Nested Rollout Policy Adaptation},
  author = {Tristan Cazenave and Jean-Baptiste Sevestre and Matthieu Toulemont},
  journal= {arXiv preprint arXiv:2101.03563},
  year   = {2021}
}

Comments

arXiv admin note: text overlap with arXiv:2003.10024

R2 v1 2026-06-23T21:57:52.121Z