# From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data

arXiv: https://arxiv.org/abs/2210.10047 · HTML: https://mlsanity.com/paper/2210.10047/

## Key facts

- Cited by 103 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 51 references that are in the map.
- First posted on arXiv 18 Oct 2022.

## Builds on (most cited first, 30 of 42)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [Offline Reinforcement Learning as One Big Sequence Modeling Problem](https://mlsanity.com/paper/2106.02039/) (2021)
- [Data-Efficient Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1805.08296/) (2018)
- [Implicit Behavioral Cloning](https://mlsanity.com/paper/2109.00137/) (2021)
- [Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning](https://mlsanity.com/paper/1910.11956/) (2019)
- [Learning Latent Plans from Play](https://mlsanity.com/paper/1903.01973/) (2019)
- [Behavior Transformers: Cloning k modes with one stone](https://mlsanity.com/paper/2206.11251/) (2022)
- [Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation](https://mlsanity.com/paper/1710.04615/) (2017)
- [Contrastive Learning as Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2206.07568/) (2022)
- [Offline Reinforcement Learning with Fisher Divergence Critic Regularization](https://mlsanity.com/paper/2103.08050/) (2021)
- [One-Shot Imitation Learning](https://mlsanity.com/paper/1703.07326/) (2017)
- [Accelerating Reinforcement Learning with Learned Skill Priors](https://mlsanity.com/paper/2010.11944/) (2020)
- [RvS: What is Essential for Offline RL via Supervised Learning?](https://mlsanity.com/paper/2112.10751/) (2021)
- [The Surprising Effectiveness of Representation Learning for Visual Imitation](https://mlsanity.com/paper/2112.01511/) (2021)
- [Parrot: Data-Driven Behavioral Priors for Reinforcement Learning](https://mlsanity.com/paper/2011.10024/) (2020)
- [Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations](https://mlsanity.com/paper/2003.06085/) (2020)
- [Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstration](https://mlsanity.com/paper/1707.02920/) (2017)
- [Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL](https://mlsanity.com/paper/2202.04478/) (2022)
- [Transformers for One-Shot Visual Imitation](https://mlsanity.com/paper/2011.05970/) (2020)

## Built on by (most cited first, 30 of 103)

- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model](https://mlsanity.com/paper/2501.15830/) (2025)
- [CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation](https://mlsanity.com/paper/2411.19650/) (2024)
- [UniVLA: Learning to Act Anywhere with Task-centric Latent Actions](https://mlsanity.com/paper/2505.06111/) (2025)
- [Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation](https://mlsanity.com/paper/2401.02117/) (2024)
- [3D Diffuser Actor: Policy Diffusion with 3D Scene Representations](https://mlsanity.com/paper/2402.10885/) (2024)
- [A Survey on Vision-Language-Action Models for Embodied AI](https://mlsanity.com/paper/2405.14093/) (2024)
- [A Cookbook of Self-Supervised Learning](https://mlsanity.com/paper/2304.12210/) (2023)
- [Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets](https://mlsanity.com/paper/2504.02792/) (2025)
- [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)
- [HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model](https://mlsanity.com/paper/2503.10631/) (2025)
- [Steering Your Diffusion Policy with Latent Space Reinforcement Learning](https://mlsanity.com/paper/2506.15799/) (2025)
- [Behavior Generation with Latent Actions](https://mlsanity.com/paper/2403.03181/) (2024)
- [iVideoGPT: Interactive VideoGPTs are Scalable World Models](https://mlsanity.com/paper/2405.15223/) (2024)
- [Open-TeleVision: Teleoperation with Immersive Active Visual Feedback](https://mlsanity.com/paper/2407.01512/) (2024)
- [Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goals](https://mlsanity.com/paper/2407.05996/) (2024)
- [Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviation](https://mlsanity.com/paper/2408.11812/) (2024)
- [Policy Representation via Diffusion Probability Model for Reinforcement Learning](https://mlsanity.com/paper/2305.13122/) (2023)
- [DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping](https://mlsanity.com/paper/2502.20900/) (2025)
- [Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations](https://mlsanity.com/paper/2303.01497/) (2023)
- [Data Quality in Imitation Learning](https://mlsanity.com/paper/2306.02437/) (2023)
- [IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI](https://mlsanity.com/paper/2411.00785/) (2024)
- [Imitating Task and Motion Planning with Visuomotor Transformers](https://mlsanity.com/paper/2305.16309/) (2023)
- [villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models](https://mlsanity.com/paper/2507.23682/) (2025)
- [Dexterity from Touch: Self-Supervised Pre-Training of Tactile Representations with Robotic Play](https://mlsanity.com/paper/2303.12076/) (2023)
- [Learning Generalizable Manipulation Policies with Object-Centric 3D Representations](https://mlsanity.com/paper/2310.14386/) (2023)
- [Robotic Skill Acquisition via Instruction Augmentation with Vision-Language Models](https://mlsanity.com/paper/2211.11736/) (2022)

## Abstract (arXiv)

While large-scale sequence modeling from offline data has led to impressive performance gains in natural language and image generation, directly translating such ideas to robotics has been challenging. One critical reason for this is that uncurated robot demonstration data, i.e. play data, collected from non-expert human demonstrators are often noisy, diverse, and distributionally multi-modal. This makes extracting useful, task-centric behaviors from such data a difficult generative modeling problem. In this work, we present Conditional Behavior Transformers (C-BeT), a method that combines the multi-modal generation ability of Behavior Transformer with future-conditioned goal specification. On a suite of simulated benchmark tasks, we find that C-BeT improves upon prior state-of-the-art work in learning from play data by an average of 45.7%. Further, we demonstrate for the first time that useful task-centric behaviors can be learned on a real-world robot purely from play data without any task labels or reward information. Robot videos are best viewed on our project website: https://play-to-policy.github.io