Generalized Nested Rollout Policy Adaptation with Limited Repetitions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Cazenave, Tristan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913200293806080
author Cazenave, Tristan
author_facet Cazenave, Tristan
contents Generalized Nested Rollout Policy Adaptation (GNRPA) is a Monte Carlo search algorithm for optimizing a sequence of choices. We propose to improve on GNRPA by avoiding too deterministic policies that find again and again the same sequence of choices. We do so by limiting the number of repetitions of the best sequence found at a given level. Experiments show that it improves the algorithm for three different combinatorial problems: Inverse RNA Folding, the Traveling Salesman Problem with Time Windows and the Weak Schur problem.
format Preprint
id arxiv_https___arxiv_org_abs_2401_10420
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generalized Nested Rollout Policy Adaptation with Limited Repetitions
Cazenave, Tristan
Artificial Intelligence
Generalized Nested Rollout Policy Adaptation (GNRPA) is a Monte Carlo search algorithm for optimizing a sequence of choices. We propose to improve on GNRPA by avoiding too deterministic policies that find again and again the same sequence of choices. We do so by limiting the number of repetitions of the best sequence found at a given level. Experiments show that it improves the algorithm for three different combinatorial problems: Inverse RNA Folding, the Traveling Salesman Problem with Time Windows and the Weak Schur problem.
title Generalized Nested Rollout Policy Adaptation with Limited Repetitions
topic Artificial Intelligence
url https://arxiv.org/abs/2401.10420