Enregistré dans:
Détails bibliographiques
Auteurs principaux: Stocco, Paula, Chundi, Suhas, Jamgochian, Arec, Kochenderfer, Mykel J.
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2403.17358
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917622169206784
author Stocco, Paula
Chundi, Suhas
Jamgochian, Arec
Kochenderfer, Mykel J.
author_facet Stocco, Paula
Chundi, Suhas
Jamgochian, Arec
Kochenderfer, Mykel J.
contents Lagrangian-guided Monte Carlo tree search with global dual ascent has been applied to solve large constrained partially observable Markov decision processes (CPOMDPs) online. In this work, we demonstrate that these global dual parameters can lead to myopic action selection during exploration, ultimately leading to suboptimal decision making. To address this, we introduce history-dependent dual variables that guide local action selection and are optimized with recursive dual ascent. We empirically compare the performance of our approach on a motivating toy example and two large CPOMDPs, demonstrating improved exploration, and ultimately, safer outcomes.
format Preprint
id arxiv_https___arxiv_org_abs_2403_17358
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Addressing Myopic Constrained POMDP Planning with Recursive Dual Ascent
Stocco, Paula
Chundi, Suhas
Jamgochian, Arec
Kochenderfer, Mykel J.
Artificial Intelligence
Lagrangian-guided Monte Carlo tree search with global dual ascent has been applied to solve large constrained partially observable Markov decision processes (CPOMDPs) online. In this work, we demonstrate that these global dual parameters can lead to myopic action selection during exploration, ultimately leading to suboptimal decision making. To address this, we introduce history-dependent dual variables that guide local action selection and are optimized with recursive dual ascent. We empirically compare the performance of our approach on a motivating toy example and two large CPOMDPs, demonstrating improved exploration, and ultimately, safer outcomes.
title Addressing Myopic Constrained POMDP Planning with Recursive Dual Ascent
topic Artificial Intelligence
url https://arxiv.org/abs/2403.17358