mlsanityData to 7 Oct 2026

Physics-informed Goal-Conditioned Reinforcement Learning under Hybrid Contact Dynamics

arXiv 2605.30503 ↗First posted 28 May 2026cs.RO cs.SY eess.SYcited by 0

Not on the map. Why?

Abstract (arXiv)

Learning to reach arbitrary goals from sparse feedback requires agents to infer a rich notion of reachability across state--goal pairs. Goal-conditioned reinforcement learning (GCRL) tackles this challenge by learning policies that generalize across goals, but this generalization becomes increasingly difficult as the underlying dynamics become high-dimensional, hybrid, or contact-dependent. To address this issue, physics-informed GCRL (Pi-GCRL) introduces optimal-control-inspired inductive biases into goal-conditioned value learning. While Pi-GCRL methods have proven effective in navigation and object-free goal-reaching domains, their reliability in contact-rich tasks remains unclear, where contact interactions induce hybrid dynamics, mode-dependent controllability, and nonsmooth value landscapes. In this work, we show that these structural properties can cause existing Pi-GCRL methods to degrade when applied naively to contact-rich manipulation. Motivated by this analysis, we introduce contact-aware and hierarchical formulations that apply physics-informed inductive biases selectively across the manipulation problem. Our results provide a principled step toward extending Pi-GCRL to contact-rich manipulation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 34 of its 45 references that are in the map. First posted on arXiv 28 May 2026.

Builds on

34 of 45 references.

References · 34

  1. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  2. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  3. 2017Hindsight Experience Replaycited by 1,096
  4. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 507
  5. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 411
  6. 2022VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Trainingcited by 384
  7. 2022Contrastive Learning as Goal-Conditioned Reinforcement Learningcited by 241
  8. 2024OGBench: Benchmarking Offline Goal-Conditioned RLcited by 216
  9. 2023LIV: Language-Image Representations and Rewards for Robotic Controlcited by 180
  10. 2020Language-Conditioned Imitation Learning for Robot Manipulation Taskscited by 136
  11. 2023HIQL: Offline Goal-Conditioned RL with Latent States as Actionscited by 133
  12. 2021Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skillscited by 125
22 more
  1. 2023Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learningcited by 116
  2. 2022Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RLcited by 89
  3. 2025Horizon Reduction Makes RL Scalablecited by 55
  4. 2021Adversarial Intrinsic Motivation for Reinforcement Learningcited by 40
  5. 2023What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?cited by 36
  6. 2024Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applicationscited by 34
  7. 2025Flow-Based Policy for Online Reinforcement Learningcited by 33
  8. 2023Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shapingcited by 25
  9. 2020An Inductive Bias for Distances: Neural Nets that Respect the Triangle Inequalitycited by 24
  10. 2025Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learningcited by 22
  11. 2020Plan2Vec: Unsupervised Representation Learning by Latent Planscited by 21
  12. 2023SMORE: Score Models for Offline Goal-Conditioned Reinforcement Learningcited by 21
  13. 2025Physics-informed Value Learner for Offline Goal-Conditioned Reinforcement Learningcited by 15
  14. 2025Goal Reaching with Eikonal-Constrained Hierarchical Quasimetric Reinforcement Learningcited by 6
  15. 2026Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusioncited by 6
  16. 2022Combining imitation and deep reinforcement learning to accomplish human-level performance on a virtual foraging taskcited by 4
  17. 2025Hyper-GoalNet: Goal-Conditioned Manipulation Policy Learning with HyperNetworkscited by 4
  18. 2025A Temporal Difference Method for Stochastic Continuous Dynamicscited by 3
  19. 2025Versatile and Generalizable Manipulation via Goal-Conditioned Reinforcement Learning with Grounded Object Detectioncited by 3
  20. 2025Automaton Constrained Q-Learningcited by 2
  21. 2026Mollified Value Learningcited by 1
  22. 2026Graph-of-Constraints Model Predictive Control for Reactive Multi-agent Task and Motion Planningcited by 1

Built on by

Not cited yet.