mlsanityData to 14 Oct 2026

LEAGUE: Guided Skill Learning and Abstraction for Long-Horizon Manipulation

arXiv 2210.12631 ↗First posted 23 Oct 2022cs.AI cs.ROcited by 34

Not on the map. Why?

Abstract (arXiv)

To assist with everyday human activities, robots must solve complex long-horizon tasks and generalize to new settings. Recent deep reinforcement learning (RL) methods show promise in fully autonomous learning, but they struggle to reach long-term goals in large environments. On the other hand, Task and Motion Planning (TAMP) approaches excel at solving and generalizing across long-horizon tasks, thanks to their powerful state and action abstractions. But they assume predefined skill sets, which limits their real-world applications. In this work, we combine the benefits of these two paradigms and propose an integrated task planning and skill learning framework named LEAGUE (Learning and Abstraction with Guidance). LEAGUE leverages the symbolic interface of a task planner to guide RL-based skill learning and creates abstract state space to enable skill reuse. More importantly, LEAGUE learns manipulation skills in-situ of the task planning system, continuously growing its capability and the set of tasks that it can solve. We evaluate LEAGUE on four challenging simulated task domains and show that LEAGUE outperforms baselines by large margins. We also show that the learned skills can be reused to accelerate learning in new tasks domains and transfer to a physical robot platform.

Key facts. Cited by 34 papers in the map (data through 14 Oct 2026). Builds on 56 of its 93 references that are in the map. First posted on arXiv 23 Oct 2022.

Builds on

56 of 93 references.

References · 56

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2015End-to-End Training of Deep Visuomotor Policiescited by 875
  3. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 743
  4. 2018Learning Dexterous In-Hand Manipulationcited by 687
  5. 2020AWAC: Accelerating Online Reinforcement Learning with Offline Datasetscited by 671
  6. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 511
  7. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 483
  8. 2018Data-Efficient Hierarchical Reinforcement Learningcited by 455
  9. 2016The Option-Critic Architecturecited by 448
  10. 2020Learning Invariant Representations for Reinforcement Learning without Reconstructioncited by 436
  11. 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 373
  12. 2016Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updatescited by 353
38 more
  1. 2017Overcoming Exploration in Reinforcement Learning with Demonstrationscited by 340
  2. 2017FeUdal Networks for Hierarchical Reinforcement Learningcited by 337
  3. 2019Emergent Tool Use From Multi-Agent Autocurriculacited by 313
  4. 2020Integrated Task and Motion Planningcited by 290
  5. 2017Automatic Goal Generation for Reinforcement Learning Agentscited by 259
  6. 2021MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scalecited by 229
  7. 2020Accelerating Reinforcement Learning with Learned Skill Priorscited by 223
  8. 2017Reverse Curriculum Generation for Reinforcement Learningcited by 198
  9. 2020OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learningcited by 166
  10. 2018PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planningcited by 150
  11. 2017Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Playcited by 141
  12. 2022Jump-Start Reinforcement Learningcited by 112
  13. 2020Learning with AMIGo: Adversarially Motivated Intrinsic Goalscited by 88
  14. 2017Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learningcited by 83
  15. 2019Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generationcited by 83
  16. 2021Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulationcited by 83
  17. 2021Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Taskscited by 78
  18. 2017Neural Task Programming: Learning to Generalize Across Hierarchical Taskscited by 76
  19. 2021Accelerating Robotic Reinforcement Learning via Parameterized Action Primitivescited by 65
  20. 2018Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstrationcited by 61
  21. 2021Learning Symbolic Operators for Task and Motion Planningcited by 58
  22. 2022Learning Neuro-Symbolic Skills for Bilevel Planningcited by 58
  23. 2018PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Makingcited by 52
  24. 2022Predicate Invention for Bilevel Planningcited by 49
  25. 2020Deep Visual Reasoning: Learning to Predict Action Sequences for Task and Motion Planning from an Initial Scene Imagecited by 48
  26. 2019Efficient Bimanual Manipulation Using Learned Task Schemascited by 45
  27. 2019DAC: The Double Actor-Critic Architecture for Learning Optionscited by 43
  28. 2021Learning Neuro-Symbolic Relational Transition Models for Bilevel Planningcited by 43
  29. 2020Deep Affordance Foresight: Planning Through What Can Be Done in the Futurecited by 41
  30. 2020Reset-Free Lifelong Learning with Skill-Space Planningcited by 38
  31. 2022Skill-based Meta-Reinforcement Learningcited by 37
  32. 2021Autonomous Reinforcement Learning via Subgoal Curriculacited by 33
  33. 2019Regression Planning Networkscited by 32
  34. 2020Sparse Graphical Memory for Robust Planningcited by 31
  35. 2018Active model learning and diverse action sampling for task and motion planningcited by 28
  36. 2021Discovery of Options via Meta-Learned Subgoalscited by 27
  37. 2022A Theory of Abstraction in Reinforcement Learningcited by 27
  38. 2020SPOTTER: Extending Symbolic Planning Operators through Targeted Reinforcement Learningcited by 23

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 10; 2025: 10; 2026: 6.

34 papers.

Sort:

By area:

  1. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulationcited by 339
  2. 2023Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planningcited by 207
  3. 2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successescited by 176
  4. 2024OAKINK2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completioncited by 82
  5. 2023Imitating Task and Motion Planning with Visuomotor Transformerscited by 66
  6. 2024Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Taskscited by 52
  7. 2023Human-in-the-Loop Task and Motion Planning for Imitation Learningcited by 29
  8. 2024A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approachescited by 20
  9. 2023Primitive Skill-based Robot Learning from Human Evaluative Feedbackcited by 15
  10. 2025Think Small, Act Big: Primitive Prompt Learning for Lifelong Robot Manipulationcited by 14
  11. 2026LiLo-VLA: Compositional Long-Horizon Manipulation via Linked Object-Centric Policiescited by 14
  12. 2023NOIR: Neural Signal Operated Intelligent Robots for Everyday Activitiescited by 8
22 more
  1. 2023NOD-TAMP: Generalizable Long-Horizon Planning with Neural Object Descriptorscited by 8
  2. 2023LHManip: A Dataset for Long-Horizon Language-Grounded Manipulation Tasks in Cluttered Tabletop Environmentscited by 7
  3. 2024PLANRL: A Motion Planning and Imitation Learning Framework to Bootstrap Reinforcement Learningcited by 6
  4. 2025Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learningcited by 4
  5. 2025LodeStar: Long-horizon Dexterity via Synthetic Data Augmentation from Human Demonstrationscited by 4
  6. 2024Exploiting Hybrid Policy in Reinforcement Learning for Interpretable Temporal Logic Manipulationcited by 3
  7. 2025Curiosity-Driven Imagination: Discovering Plan Operators and Learning Associated Policies for Open-World Adaptationcited by 3
  8. 2025Impedance Primitive-augmented Hierarchical Reinforcement Learning for Sequential Taskscited by 3
  9. 2025SLAP: Shortcut Learning for Abstract Planningcited by 3
  10. 2025Learning Long-Horizon Robot Manipulation Skills via Privileged Actioncited by 2
  11. 2025Few-Shot Neuro-Symbolic Imitation Learning for Long-Horizon Planning and Actingcited by 2
  12. 2023Program Machine Policy: Addressing Long-Horizon Tasks by Integrating Program Synthesis and State Machinescited by 1
  13. 2024Learning to Bridge the Gap: Efficient Novelty Recovery with Planning and Reinforcement Learningcited by 1
  14. 2024Implicit Contact Diffuser: Sequential Contact Reasoning with Latent Point Cloud Diffusioncited by 1
  15. 2026Novelty Adaptation Through Hybrid Large Language Model (LLM)-Symbolic Planning and LLM-guided Reinforcement Learningcited by 1
  16. 2024Learning the Generalizable Manipulation Skills on Soft-body Tasks via Guided Self-attention Behavior Cloning Policycited by 0
  17. 2025Task and Skill Planning: Hierarchical Robot Planning with Black-Box Skillscited by 0
  18. 2025NOIR 2.0: Neural Signal Operated Intelligent Robots for Everyday Activitiescited by 0
  19. 2026Build on Priors: Vision--Language--Guided Neuro-Symbolic Imitation Learning for Data-Efficient Real-World Robot Manipulationcited by 0
  20. 2026Regression Test Selection for Updated Capability Modules in Compositional ML Systems via Atomic-Quality Probescited by 0
  21. 2026Human2Any: Human-to-Robot Transfer via Constraint-Aware Compositional Planningcited by 0
  22. 2026From Rollout to Reset: A Graph-Based Harness for Autonomous Long-Horizon Manipulation Evaluationcited by 0