mlsanityData to 7 Oct 2026

TACO: Learning Task Decomposition via Temporal Alignment for Control

arXiv 1803.01840 ↗First posted 2 Mar 2018cs.LG stat.MLcited by 61

On the map: Offline RL and imitation learning from data → Robot learning from demonstration

Abstract (arXiv)

Many advanced Learning from Demonstration (LfD) methods consider the decomposition of complex, real-world tasks into simpler sub-tasks. By reusing the corresponding sub-policies within and between tasks, they provide training data for each policy from different high-level tasks and compose them to perform novel ones. Existing approaches to modular LfD focus either on learning a single high-level task or depend on domain knowledge and temporal segmentation. In contrast, we propose a weakly supervised, domain-agnostic approach based on task sketches, which include only the sequence of sub-tasks performed in each demonstration. Our approach simultaneously aligns the sketches with the observed demonstrations and learns the required sub-policies. This improves generalisation in comparison to separate optimisation procedures. We evaluate the approach on multiple domains, including a simulated 3D robot arm control task using purely image-based observations. The results show that our approach performs commensurately with fully supervised approaches, while requiring significantly less annotation effort.

Key facts. Cited by 61 papers in the map (data through 7 Oct 2026). Placed in Robot learning from demonstration, one of 13 directions in Offline RL and imitation learning from data. First posted on arXiv 2 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 3; 2019: 1; 2020: 2; 2021: 9; 2022: 16; 2023: 10; 2024: 7; 2025: 10; 2026: 3.

61 papers.

Sort:

By area:

  1. 2023MimicPlay: Long-Horizon Imitation Learning by Watching Human Playcited by 214
  2. 2023SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Modelscited by 151
  3. 2022Prompting Decision Transformer for Few-Shot Policy Generalizationcited by 143
  4. 2021Skill Induction and Planning with Latent Languagecited by 99
  5. 2021Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulationcited by 82
  6. 2022BITS: Bi-level Imitation for Traffic Simulationcited by 80
  7. 2022Learning and Retrieval from Prior Data for Skill-based Imitation Learningcited by 77
  8. 2023XSkill: Cross Embodiment Skill Discoverycited by 74
  9. 2023LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discoverycited by 63
  10. 2022Skill-based Model-based Reinforcement Learningcited by 50
  11. 2018One-Shot Hierarchical Imitation Learning of Compound Visuomotor Taskscited by 32
  12. 2023Human-in-the-Loop Task and Motion Planning for Imitation Learningcited by 28
38 more
  1. 2021Learning Transferable Motor Skills with Hierarchical Latent Mixture Policiescited by 26
  2. 2023Universal Visual Decomposer: Long-Horizon Manipulation Made Easycited by 23
  3. 2022Learning Options via Compressioncited by 22
  4. 2020Active Task-Inference-Guided Deep Inverse Reinforcement Learningcited by 17
  5. 2021Learning Task Decomposition with Ordered Memory Policy Networkcited by 15
  6. 2022Unsupervised Learning of Temporal Abstractions with Slot-based Transformerscited by 14
  7. 2024Scaling Robot Policy Learning via Zero-Shot Labeling with Foundation Modelscited by 14
  8. 2024EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Datacited by 13
  9. 2024STEER: Flexible Robotic Manipulation via Dense Language Groundingcited by 13
  10. 2021Inverse Contextual Bandits: Learning How Behavior Evolves over Timecited by 12
  11. 2022Bayes risk CTC: Controllable CTC alignment in Sequence-to-Sequence taskscited by 12
  12. 2021Generalization in Text-based Games via Hierarchical Reinforcement Learningcited by 11
  13. 2020Provable Hierarchical Imitation Learning via EMcited by 10
  14. 2022Perceiving the World: Question-guided Reinforcement Learning for Text-based Gamescited by 10
  15. 2022MO2: Model-Based Offline Optionscited by 10
  16. 2019Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learningcited by 8
  17. 2024PRIME: Scaffolding Manipulation Tasks with Behavior Primitives for Data-Efficient Imitation Learningcited by 8
  18. 2025REMAC: Self-Reflective and Self-Evolving Multi-Agent Collaboration for Long-Horizon Robot Manipulationcited by 8
  19. 2018CompILE: Compositional Imitation Learning and Executioncited by 7
  20. 2024DeformPAM: Data-Efficient Learning for Long-horizon Deformable Object Manipulation via Preference-based Action Alignmentcited by 7
  21. 2025BOSS: Benchmark for Observation Space Shift in Long-Horizon Taskcited by 7
  22. 2025Open-World Skill Discovery from Unsegmented Demonstrationscited by 7
  23. 2022Learning Sensorimotor Primitives of Sequential Manipulation Tasks from Visual Demonstrationscited by 6
  24. 2022SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Explorationcited by 6
  25. 2021Contextualizing Meta-Learning via Learning to Decomposecited by 5
  26. 2022Bayesian Nonparametrics for Offline Skill Discoverycited by 5
  27. 2022Possibility Before Utility: Learning And Using Hierarchical Affordancescited by 4
  28. 2025Shared Autonomy for Proximal Teachingcited by 4
  29. 2025Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learningcited by 4
  30. 2025ESPADA: Execution Speedup via Semantics Aware Demonstration Data Downsampling for Imitation Learningcited by 4
  31. 2023Hierarchical Imitation Learning for Stochastic Environmentscited by 3
  32. 2024SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Taskscited by 3
  33. 2021AutoPreview: A Framework for Autopilot Behavior Understandingcited by 2
  34. 2022Leveraging Demonstrations with Latent Space Priorscited by 2
  35. 2023CRISP: Curriculum Inducing Primitive Informed Subgoal Prediction for Hierarchical Reinforcement Learningcited by 2
  36. 2023PEAR: Primitive Enabled Adaptive Relabeling for Boosting Hierarchical Reinforcement Learningcited by 2
  37. 2024RAG-based Crowdsourcing Task Decomposition via Masked Contrastive Learning with Promptscited by 2
  38. 2018Generalizing Robot Imitation Learning with Invariant Hidden Semi-Markov Modelscited by 1

50 most cited of 61 All 61 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026SparTa: Sparse Graphical Task Models from a Handful of Demonstrations
  2. 2025An Alignment-Based Approach to Learning Motions from Demonstrations
  3. 2023Learning from Few Demonstrations with Frame-Weighted Motion Generation
  4. 2021Learning Forceful Manipulation Skills from Multi-modal Human Demonstrations
  5. 2026Decompose and Reorganize: Planning with Primitives and Visuomotor Policies Learned from Demonstrations ↗
  6. 2018Learning Generalizable Robot Skills from Demonstrations in Cluttered Environments
  7. 2024Towards Improving Learning from Demonstration Algorithms via MCMC Methods
  8. 2026Task Parameter Extrapolation via Learning Inverse Tasks from Forward Demonstrations ↗