mlsanityData to 7 Oct 2026

STAP: Sequencing Task-Agnostic Policies

arXiv 2210.12250 ↗First posted 21 Oct 2022cs.RO cs.AIcited by 17

Not on the map. Why?

Abstract (arXiv)

Advances in robotic skill acquisition have made it possible to build general-purpose libraries of learned skills for downstream manipulation tasks. However, naively executing these skills one after the other is unlikely to succeed without accounting for dependencies between actions prevalent in long-horizon plans. We present Sequencing Task-Agnostic Policies (STAP), a scalable framework for training manipulation skills and coordinating their geometric dependencies at planning time to solve long-horizon tasks never seen by any skill during training. Given that Q-functions encode a measure of skill feasibility, we formulate an optimization problem to maximize the joint success of all skills sequenced in a plan, which we estimate by the product of their Q-values. Our experiments indicate that this objective function approximates ground truth plan feasibility and, when used as a planning objective, reduces myopic behavior and thereby promotes long-horizon task success. We further demonstrate how STAP can be used for task and motion planning by estimating the geometric feasibility of skill sequences provided by a task planner. We evaluate our approach in simulation and on a real robot. Qualitative results and code are made available at https://sites.google.com/stanford.edu/stap.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 47 of its 83 references that are in the map. First posted on arXiv 21 Oct 2022.

Builds on

47 of 83 references.

References · 47

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  2. 2015Continuous control with deep reinforcement learningcited by 3,279
  3. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  4. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  5. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  6. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,179
  7. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 753
  8. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 748
  9. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  10. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
  11. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 678
  12. 2018Data-Efficient Hierarchical Reinforcement Learningcited by 436
35 more
  1. 2016The Option-Critic Architecturecited by 433
  2. 2020Planning to Explore via Self-Supervised World Modelscited by 365
  3. 2019Dynamics-Aware Unsupervised Discovery of Skillscited by 308
  4. 2021Ensemble deep learning: A reviewcited by 283
  5. 2020Integrated Task and Motion Planningcited by 281
  6. 2016Deep Visual Foresight for Planning Robot Motioncited by 276
  7. 2021MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scalecited by 226
  8. 2020Accelerating Reinforcement Learning with Learned Skill Priorscited by 220
  9. 2020OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learningcited by 164
  10. 2020Parrot: Data-Driven Behavioral Priors for Reinforcement Learningcited by 136
  11. 2021Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skillscited by 125
  12. 2017Neural Task Programming: Learning to Generalize Across Hierarchical Taskscited by 75
  13. 2021Greedy Hierarchical Variational Autoencoders for Large-Scale Video Predictioncited by 75
  14. 2021Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Taskscited by 75
  15. 2021Accelerating Robotic Reinforcement Learning via Parameterized Action Primitivescited by 63
  16. 2015Reinforcement Learning with Parameterized Actionscited by 61
  17. 2018Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstrationcited by 60
  18. 2020Neural Dynamic Policies for End-to-End Sensorimotor Learningcited by 56
  19. 2020Learning Robot Skills with Temporal Variational Inferencecited by 54
  20. 2020Learning compositional models of robot skills for task and motion planningcited by 47
  21. 2020Deep Visual Reasoning: Learning to Predict Action Sequences for Task and Motion Planning from an Initial Scene Imagecited by 45
  22. 2019Efficient Bimanual Manipulation Using Learned Task Schemascited by 44
  23. 2021AW-Opt: Learning Robotic Skills with Imitation and Reinforcement at Scalecited by 43
  24. 2020Deep Affordance Foresight: Planning Through What Can Be Done in the Futurecited by 41
  25. 2020Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networkscited by 38
  26. 2021Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networkscited by 32
  27. 2018Active model learning and diverse action sampling for task and motion planningcited by 28
  28. 2020Bayesian Robust Optimization for Imitation Learningcited by 28
  29. 2021Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoningcited by 25
  30. 2020A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objectscited by 22
  31. 2022Generalizable Task Planning through Representation Pretrainingcited by 19
  32. 2020CAMPs: Learning Context-Specific Abstractions for Efficient Planning in Factored MDPscited by 18
  33. 2021Hierarchical Neural Dynamic Policiescited by 17
  34. 2021Example-Driven Model-Based Reinforcement Learning for Solving Long-Horizon Visuomotor Taskscited by 12
  35. 2022Symbolic State Estimation with Predicates for Contact-Rich Manipulation Taskscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 4; 2025: 5; 2026: 2.

17 papers.

Sort:

By area:

  1. 2023Text2Motion: From Natural Language Instructions to Feasible Planscited by 223
  2. 2023Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agentscited by 66
  3. 2025Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulationcited by 48
  4. 2023Sequential Dexterity: Chaining Dexterous Policies for Long-Horizon Manipulationcited by 43
  5. 2023KITE: Keypoint-Conditioned Policies for Semantic Manipulationcited by 39
  6. 2024Trust the PRoC3S: Solving Long-Horizon Robotics Problems with LLMs and Constraint Satisfactioncited by 19
  7. 2023Primitive Skill-based Robot Learning from Human Evaluative Feedbackcited by 15
  8. 2024Open-World Task and Motion Planning via Vision-Language Model Generated Constraintscited by 9
  9. 2024What's the Move? Hybrid Imitation Learning via Salient Pointscited by 9
  10. 2023Robot Task Planning Based on Large Language Model Representing Knowledge with Directed Graph Structurescited by 7
  11. 2024LIT: Large Language Model Driven Intention Tracking for Proactive Human-Robot Collaboration -- A Robot Sous-Chef Applicationcited by 3
  12. 2025SLAP: Shortcut Learning for Abstract Planningcited by 3
5 more
  1. 2026ManiSkillFormer: Demonstration-Free Compositional Manipulation via Geometric Contracts and Agentic Skill Graphcited by 1
  2. 2025Task and Skill Planning: Hierarchical Robot Planning with Black-Box Skillscited by 0
  3. 2025From Shadow to Light: Toward Safe and Efficient Policy Learning Across MPC, DeePC, RL, and LLM Agentscited by 0
  4. 2025NOIR 2.0: Neural Signal Operated Intelligent Robots for Everyday Activitiescited by 0
  5. 2026DistAL: Distance-based Advantage Learning for VLA Fine-Tuningcited by 0