Paper ID: 2407.01991

Generation of Geodesics with Actor-Critic Reinforcement Learning to Predict Midpoints

Kazumi Kasaura

To find the shortest paths for all pairs on manifolds with infinitesimally defined metrics, we propose to generate them by predicting midpoints recursively and an actor-critic method to learn midpoint prediction. We prove the soundness of our approach and show experimentally that the proposed method outperforms existing methods on both local and global path planning tasks.

Submitted: Jul 2, 2024