# Learning Latent Plans from Play

arXiv: https://arxiv.org/abs/1903.01973 · HTML: https://mlsanity.com/paper/1903.01973/

## Key facts

- Cited by 316 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Mar 2019.

## Built on by (most cited first, 30 of 316)

- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks](https://mlsanity.com/paper/2112.03227/) (2021)
- [MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations](https://mlsanity.com/paper/2310.17596/) (2023)
- [Latent Action Pretraining from Videos](https://mlsanity.com/paper/2410.11758/) (2024)
- [Behavior Transformers: Cloning k modes with one stone](https://mlsanity.com/paper/2206.11251/) (2022)
- [A Survey on Vision-Language-Action Models for Embodied AI](https://mlsanity.com/paper/2405.14093/) (2024)
- [Contrastive Learning as Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2206.07568/) (2022)
- [OGBench: Benchmarking Offline Goal-Conditioned RL](https://mlsanity.com/paper/2410.20092/) (2024)
- [Goal-Conditioned Imitation Learning using Score-based Diffusion Policies](https://mlsanity.com/paper/2304.02532/) (2023)
- [MimicPlay: Long-Horizon Imitation Learning by Watching Human Play](https://mlsanity.com/paper/2302.12422/) (2023)
- [Interactive Language: Talking to Robots in Real Time](https://mlsanity.com/paper/2210.06407/) (2022)
- [RT-H: Action Hierarchies Using Language](https://mlsanity.com/paper/2403.01823/) (2024)
- [Language Conditioned Imitation Learning over Unstructured Data](https://mlsanity.com/paper/2005.07648/) (2020)
- [RvS: What is Essential for Offline RL via Supervised Learning?](https://mlsanity.com/paper/2112.10751/) (2021)
- [RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunking](https://mlsanity.com/paper/2309.01918/) (2023)
- [OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning](https://mlsanity.com/paper/2010.13611/) (2020)
- [Foundation Models for Decision Making: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2303.04129/) (2023)
- [Behavior Generation with Latent Actions](https://mlsanity.com/paper/2403.03181/) (2024)
- [Episodic Transformer for Vision-and-Language Navigation](https://mlsanity.com/paper/2105.06453/) (2021)
- [mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs](https://mlsanity.com/paper/2512.15692/) (2025)
- [HIQL: Offline Goal-Conditioned RL with Latent States as Actions](https://mlsanity.com/paper/2307.11949/) (2023)
- [What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Data](https://mlsanity.com/paper/2204.06252/) (2022)
- [Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goals](https://mlsanity.com/paper/2407.05996/) (2024)
- [RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches](https://mlsanity.com/paper/2311.01977/) (2023)
- [Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills](https://mlsanity.com/paper/2104.07749/) (2021)
- [Rapid Exploration for Open-World Navigation with Latent Goal Models](https://mlsanity.com/paper/2104.05859/) (2021)
- [DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning](https://mlsanity.com/paper/2410.24185/) (2024)
- [Generalized Decision Transformer for Offline Hindsight Information Matching](https://mlsanity.com/paper/2111.10364/) (2021)
- [DALL-E-Bot: Introducing Web-Scale Diffusion Models to Robotics](https://mlsanity.com/paper/2210.02438/) (2022)

## 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