Stabilized Nested Rollout Policy Adaptation

2021/01/01 by Tristan Cazenave, Cazenave, Tristan, Jean-Baptiste Sevestre +3 · 1 voice · 1 citation
Computer Science · Economics, Econometrics and Finance · Social Sciences · #Artificial Intelligence in Games #Digital Games and Media #Sports Analytics and Performance

paper · doi:10.1007/978-3-030-89453-5_2

crossref issued 2021/01/01 · crossref published 2021/01/01 · crossref published-print 2021/01/01 · openalex publication_date 2021/01/01 · crossref published-online 2021/10/16 · crossref created 2021/11/29 · crossref deposited 2023/11/13 · crossref indexed 2025/03/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29

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.

Cited by

• Pareto-NRPA: A Novel Monte-Carlo Search Algorithm for Multi-Objective Optimization

Discussions

• 📖 New LAMSADE paper: Stabilized Nested Rollout Policy Adaptation. (MCS@IJCAI) https://doi.org/10.1007/978-3-030-89453-5_2 [bsky, 1 points, 0 comments]