Entropy-regularized Point-based Value Iteration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Delecki, Harrison, Vazquez-Chanlatte, Marcell, Yel, Esen, Wray, Kyle, Arnon, Tomer, Witwicki, Stefan, Kochenderfer, Mykel J.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929243420622848
author Delecki, Harrison
Vazquez-Chanlatte, Marcell
Yel, Esen
Wray, Kyle
Arnon, Tomer
Witwicki, Stefan
Kochenderfer, Mykel J.
author_facet Delecki, Harrison
Vazquez-Chanlatte, Marcell
Yel, Esen
Wray, Kyle
Arnon, Tomer
Witwicki, Stefan
Kochenderfer, Mykel J.
contents Model-based planners for partially observable problems must accommodate both model uncertainty during planning and goal uncertainty during objective inference. However, model-based planners may be brittle under these types of uncertainty because they rely on an exact model and tend to commit to a single optimal behavior. Inspired by results in the model-free setting, we propose an entropy-regularized model-based planner for partially observable problems. Entropy regularization promotes policy robustness for planning and objective inference by encouraging policies to be no more committed to a single action than necessary. We evaluate the robustness and objective inference performance of entropy-regularized policies in three problem domains. Our results show that entropy-regularized policies outperform non-entropy-regularized baselines in terms of higher expected returns under modeling errors and higher accuracy during objective inference.
format Preprint
id arxiv_https___arxiv_org_abs_2402_09388
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Entropy-regularized Point-based Value Iteration
Delecki, Harrison
Vazquez-Chanlatte, Marcell
Yel, Esen
Wray, Kyle
Arnon, Tomer
Witwicki, Stefan
Kochenderfer, Mykel J.
Artificial Intelligence
Model-based planners for partially observable problems must accommodate both model uncertainty during planning and goal uncertainty during objective inference. However, model-based planners may be brittle under these types of uncertainty because they rely on an exact model and tend to commit to a single optimal behavior. Inspired by results in the model-free setting, we propose an entropy-regularized model-based planner for partially observable problems. Entropy regularization promotes policy robustness for planning and objective inference by encouraging policies to be no more committed to a single action than necessary. We evaluate the robustness and objective inference performance of entropy-regularized policies in three problem domains. Our results show that entropy-regularized policies outperform non-entropy-regularized baselines in terms of higher expected returns under modeling errors and higher accuracy during objective inference.
title Entropy-regularized Point-based Value Iteration
topic Artificial Intelligence
url https://arxiv.org/abs/2402.09388