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

2024-07-02 · 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.

📄 PDF Abstract BibTeX arXiv:2407.01991

Code (1)

omron-sinicx/midpoint_learning 공식 구현 pytorch

Tasks

reinforcement-learning

Learning Mean-Field Games through Mean-Field Actor-Critic Flow

2025-10-14 · Mo Zhou, Haosheng Zhou, Ruimeng Hu arxiv

We propose the Mean-Field Actor-Critic (MFAC) flow, a continuous-time learning dynamics for solving mean-field games (MFGs), combining techniques from reinforcement learning and optimal transport. The MFAC framework join…

Reinforcement Learning

NeuroGF: A Neural Representation for Fast Geodesic Distance and Path Queries

2023-06-01 · NeurIPS 2023 11 · Qijian Zhang, Junhui Hou, Yohanes Yudhi Adikusuma, Wenping Wang 외

Geodesics are essential in many geometry processing applications. However, traditional algorithms for computing geodesic distances and paths on 3D mesh models are often inefficient and slow. This makes them impractical f…

3D geometry

Predictive Traffic Rule Compliance using Reinforcement Learning

2025-03-29 · Yanliang Huang, Sebastian Mair, Zhuoqi Zeng, Matthias Althoff

Autonomous vehicle path planning has reached a stage where safety and regulatory compliance are crucial. This paper presents an approach that integrates a motion planner with a deep reinforcement learning model to predic…

Deep Reinforcement Learning Motion Planning reinforcement-learning Reinforcement Learning

A deep learning framework for geodesics under spherical Wasserstein-Fisher-Rao metric and its application for weighted sample generation

2022-08-25 · Yang Jing, Jiaheng Chen, Lei LI, Jianfeng Lu

Wasserstein-Fisher-Rao (WFR) distance is a family of metrics to gauge the discrepancy of two Radon measures, which takes into account both transportation and weight change. Spherical WFR distance is a projected version o…

Bayesian Inference

An Actor-Critic Algorithm for Sequence Prediction

2016-07-24 · Dzmitry Bahdanau, Philemon Brakel, Kelvin Xu, Anirudh Goyal 외

We present an approach to training neural networks to generate sequences using actor-critic methods from reinforcement learning (RL). Current log-likelihood training methods are limited by the discrepancy between their t…

Caption Generation Machine Translation Prediction Reinforcement Learning+4