mlsanityData to 7 Oct 2026

Learning Latent Plans from Play

arXiv 1903.01973 ↗First posted 5 Mar 2019cs.ROcited by 310

Not on the map. Why?

Cited by 106 in Offline RL and imitation learning from data, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Acquiring a diverse repertoire of general-purpose skills remains an open challenge for robotics. In this work, we propose self-supervising control on top of human teleoperated play data as a way to scale up skill learning. Play has two properties that make it attractive compared to conventional task demonstrations. Play is cheap, as it can be collected in large quantities quickly without task segmenting, labeling, or resetting to an initial state. Play is naturally rich, covering ~4x more interaction space than task demonstrations for the same amount of collection time. To learn control from play, we introduce Play-LMP, a self-supervised method that learns to organize play behaviors in a latent space, then reuse them at test time to achieve specific goals. Combining self-supervised control with a diverse play dataset shifts the focus of skill learning from a narrow and discrete set of tasks to the full continuum of behaviors available in an environment. We find that this combination generalizes well empirically---after self-supervising on unlabeled play, our method substantially outperforms individual expert-trained policies on 18 difficult user-specified visual manipulation tasks in a simulated robotic tabletop environment. We additionally find that play-supervised models, unlike their expert-trained counterparts, are more robust to perturbations and exhibit retrying-till-success behaviors. Finally, we find that our agent organizes its latent plan space around functional tasks, despite never being trained with task labels. Videos, code and data are available at learning-from-play.github.io

Key facts. Cited by 310 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 4; 2021: 37; 2022: 56; 2023: 61; 2024: 51; 2025: 54; 2026: 46.

310 papers.

Sort:

By area:

  1. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,406
  2. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningcited by 738
  3. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 564
  4. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 308
  5. 2024Latent Action Pretraining from Videoscited by 302
  6. 2022Behavior Transformers: Cloning k modes with one stonecited by 299
  7. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 274
  8. 2022Contrastive Learning as Goal-Conditioned Reinforcement Learningcited by 241
  9. 2023Goal-Conditioned Imitation Learning using Score-based Diffusion Policiescited by 229
  10. 2022Interactive Language: Talking to Robots in Real Timecited by 217
  11. 2024OGBench: Benchmarking Offline Goal-Conditioned RLcited by 216
  12. 2023MimicPlay: Long-Horizon Imitation Learning by Watching Human Playcited by 214
38 more
  1. 2020Language Conditioned Imitation Learning over Unstructured Datacited by 208
  2. 2024RT-H: Action Hierarchies Using Languagecited by 204
  3. 2021RvS: What is Essential for Offline RL via Supervised Learning?cited by 184
  4. 2023RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunkingcited by 167
  5. 2020OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learningcited by 164
  6. 2023Foundation Models for Decision Making: Problems, Methods, and Opportunitiescited by 160
  7. 2024Behavior Generation with Latent Actionscited by 159
  8. 2021Episodic Transformer for Vision-and-Language Navigationcited by 155
  9. 2022What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Datacited by 137
  10. 2023HIQL: Offline Goal-Conditioned RL with Latent States as Actionscited by 133
  11. 2025mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAscited by 133
  12. 2023RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketchescited by 131
  13. 2024Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goalscited by 131
  14. 2021Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skillscited by 125
  15. 2021Rapid Exploration for Open-World Navigation with Latent Goal Modelscited by 118
  16. 2021Generalized Decision Transformer for Offline Hindsight Information Matchingcited by 105
  17. 2022DALL-E-Bot: Introducing Web-Scale Diffusion Models to Roboticscited by 105
  18. 2024DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learningcited by 104
  19. 2022Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RLcited by 103
  20. 2022From Play to Policy: Conditional Behavior Generation from Uncurated Robot Datacited by 103
  21. 2022Grounding Language with Visual Affordances over Unstructured Datacited by 101
  22. 2023Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysiscited by 99
  23. 2022Instruction-driven history-aware policies for robotic manipulationscited by 93
  24. 2022Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RLcited by 89
  25. 2022Latent Plans for Task-Agnostic Offline Reinforcement Learningcited by 81
  26. 2022BITS: Bi-level Imitation for Traffic Simulationcited by 80
  27. 2022Learning and Retrieval from Prior Data for Skill-based Imitation Learningcited by 77
  28. 2025Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Modelscited by 77
  29. 2022Dexterous Imitation Made Easy: A Learning-Based Framework for Efficient Dexterous Manipulationcited by 75
  30. 2023XSkill: Cross Embodiment Skill Discoverycited by 74
  31. 2021Demonstration-Guided Reinforcement Learning with Learned Skillscited by 73
  32. 2025Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policycited by 73
  33. 2023Data Quality in Imitation Learningcited by 72
  34. 2024The Ingredients for Robotic Diffusion Transformerscited by 72
  35. 2021Asymmetric self-play for automatic goal discovery in robotic manipulationcited by 71
  36. 2022CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation Learningcited by 70
  37. 2022How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via f-Advantage Regressioncited by 65
  38. 2021UMPNet: Universal Manipulation Policy Network for Articulated Objectscited by 64

50 most cited of 310 All 310 (JSON)