mlsanityData to 14 Oct 2026

Multi-Task Option Learning and Discovery for Stochastic Path Planning

arXiv 2210.00068 ↗First posted 30 Sep 2022cs.LG cs.AI cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper addresses the problem of reliably and efficiently solving broad classes of long-horizon stochastic path planning problems. Starting with a vanilla RL formulation with a stochastic dynamics simulator and an occupancy matrix of the environment, our approach computes useful options with policies as well as high-level paths that compose the discovered options. Our main contributions are (1) data-driven methods for creating abstract states that serve as endpoints for helpful options, (2) methods for computing option policies using auto-generated option guides in the form of dense pseudo-reward functions, and (3) an overarching algorithm for composing the computed options. We show that this approach yields strong guarantees of executability and solvability: under fairly general conditions, the computed option guides lead to composable option policies and consequently ensure downward refinability. Empirical evaluation on a range of robots, environments, and tasks shows that this approach effectively transfers knowledge across related tasks and that it outperforms existing approaches by a significant margin.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 51 references that are in the map. First posted on arXiv 30 Sep 2022.

Builds on

25 of 51 references.

References · 25

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  4. 2015Continuous control with deep reinforcement learningcited by 3,407
  5. 2017Hindsight Experience Replaycited by 1,136
  6. 2018Data-Efficient Hierarchical Reinforcement Learningcited by 455
  7. 2016The Option-Critic Architecturecited by 448
  8. 2016Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivationcited by 286
  9. 2019Search on the Replay Buffer: Bridging Planning and Reinforcement Learningcited by 194
  10. 2016Value Iteration Networkscited by 160
  11. 2018Near-Optimal Representation Learning for Hierarchical Reinforcement Learningcited by 110
  12. 2018Temporal Difference Models: Model-Free Deep RL for Model-Based Controlcited by 89
13 more
  1. 2018SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planningcited by 78
  2. 2018Learning Plannable Representations with Causal InfoGANcited by 57
  3. 2018PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Makingcited by 52
  4. 2021Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learningcited by 47
  5. 2020Sub-Goal Trees -- a Framework for Goal-Based Reinforcement Learningcited by 29
  6. 2019Learning from Trajectories via Subgoal Discoverycited by 28
  7. 2019Harnessing Reinforcement Learning for Neural Motion Planningcited by 21
  8. 2021Subgoal Search For Complex Reasoning Taskscited by 21
  9. 2018Finding Options that Minimize Planning Timecited by 17
  10. 2019Learn and Link: Learning Critical Regions for Efficient Planningcited by 7
  11. 2022Safely: Safe Stochastic Motion Planning Under Constrained Sensing via Dualitycited by 3
  12. 2021AMRA*: Anytime Multi-Resolution Multi-Heuristic A*cited by 2
  13. 2022Using Deep Learning to Bootstrap Abstractions for Hierarchical Robot Planningcited by 2

Built on by

Not cited yet.