mlsanityData to 14 Oct 2026

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

arXiv 2407.01991 ↗First posted 2 Jul 2024cs.LG cs.AIcited by 1

On the map: Deep reinforcement learning methods → RL theory and sample complexity

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods. Builds on 12 of its 48 references that are in the map. First posted on arXiv 2 Jul 2024.

Builds on

12 of 48 references.

References · 12

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  4. 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 664
  5. 2023Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learningcited by 121
  6. 2020Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictorscited by 62
  7. 2020Is Long Horizon Reinforcement Learning More Difficult Than Short Horizon Reinforcement Learning?cited by 35
  8. 2020Sub-Goal Trees -- a Framework for Goal-Based Reinforcement Learningcited by 29
  9. 2020Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planningcited by 19
  10. 2018Floyd-Warshall Reinforcement Learning: Learning from Past Experiences to Reach New Goalscited by 8
  11. 2021On Linear Interpolation in the Latent Space of Deep Generative Modelscited by 8
  12. 2021A Reinforcement Learning based Path Planning Approach in 3D Environmentcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Hierarchical Soft Actor-Critic for Sparse-Reward Long-Horizon Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025GRL-SNAM: Geometric Reinforcement Learning with Path Differential Hamiltonians for Simultaneous Navigation and Mapping in Unknown Environments
  2. 2026A Geometric Approach to Soft Actor-Critic with Zonotopes for Locomotion Learning
  3. 2026Learning from Demonstrations over Riemannian Manifolds using Neural ODEs: An Extended Abstract ↗
  4. 2026GeoWorld: Geometric World Models
  5. 2024FootstepNet: an Efficient Actor-Critic Method for Fast On-line Bipedal Footstep Planning and Forecasting
  6. 2026Guided Riemannian Optimization (GuRO): Bridging Model Predictive Control and Decision Transformers
  7. 2025Abstracting Geo-specific Terrains to Scale Up Reinforcement Learning
  8. 2025Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces