Saved in:
Bibliographic Details
Main Author: Miyaguchi, Kohei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.19375
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912446661263360
author Miyaguchi, Kohei
author_facet Miyaguchi, Kohei
contents In this paper, we propose trajectory advantage regression, a method of offline path learning and path attribution based on reinforcement learning. The proposed method can be used to solve path optimization problems while algorithmically only solving a regression problem.
format Preprint
id arxiv_https___arxiv_org_abs_2506_19375
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Path Learning with Trajectory Advantage Regression
Miyaguchi, Kohei
Machine Learning
In this paper, we propose trajectory advantage regression, a method of offline path learning and path attribution based on reinforcement learning. The proposed method can be used to solve path optimization problems while algorithmically only solving a regression problem.
title Path Learning with Trajectory Advantage Regression
topic Machine Learning
url https://arxiv.org/abs/2506.19375