JMLR
Generation of Geodesics with Actor-Critic Reinforcement Learning to Predict Midpoints
Authors
Kazumi Kasaura
Paper Information
-
Journal:
Journal of Machine Learning Research -
Added to Tracker:
Dec 30, 2025
Abstract
To find the shortest paths for all pairs on manifolds with infinitesimally defined metrics, we introduce a framework to generate them by predicting midpoints recursively. To learn midpoint prediction, we propose an actor-critic approach. We prove the soundness of our approach and show experimentally that the proposed method outperforms existing methods on several planning tasks, including path planning for agents with complex kinematics and motion planning for multi-degree-of-freedom robot arms.
Author Details
Kazumi Kasaura
AuthorCitation Information
APA Format
Kazumi Kasaura
.
Generation of Geodesics with Actor-Critic Reinforcement Learning to Predict Midpoints.
Journal of Machine Learning Research
.
BibTeX Format
@article{paper718,
title = { Generation of Geodesics with Actor-Critic Reinforcement Learning to Predict Midpoints },
author = {
Kazumi Kasaura
},
journal = { Journal of Machine Learning Research },
url = { https://www.jmlr.org/papers/v26/24-1020.html }
}