# Affordance Learning from Play for Sample-Efficient Policy Learning

arXiv: https://arxiv.org/abs/2203.00352 · HTML: https://mlsanity.com/paper/2203.00352/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 35 references that are in the map.
- First posted on arXiv 1 Mar 2022.

## Builds on (most cited first, 29 of 29)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes](https://mlsanity.com/paper/1711.00199/) (2017)
- [QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation](https://mlsanity.com/paper/1806.10293/) (2018)
- [PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding](https://mlsanity.com/paper/1812.02713/) (2018)
- [Time-Contrastive Networks: Self-Supervised Learning from Video](https://mlsanity.com/paper/1704.06888/) (2017)
- [Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection](https://mlsanity.com/paper/1603.02199/) (2016)
- [Learning Latent Plans from Play](https://mlsanity.com/paper/1903.01973/) (2019)
- [Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects](https://mlsanity.com/paper/1809.10790/) (2018)
- [Where2Act: From Pixels to Actions for Articulated 3D Objects](https://mlsanity.com/paper/2101.02692/) (2021)
- [Residual Policy Learning](https://mlsanity.com/paper/1812.06298/) (2018)
- [Grounded Human-Object Interaction Hotspots from Video](https://mlsanity.com/paper/1812.04558/) (2018)
- [AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection](https://mlsanity.com/paper/1709.07326/) (2017)
- [Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching](https://mlsanity.com/paper/1710.01330/) (2017)
- [End-to-End Robotic Reinforcement Learning without Reward Engineering](https://mlsanity.com/paper/1904.07854/) (2019)
- [Deep Learning for Detecting Robotic Grasps](https://mlsanity.com/paper/1301.3592/) (2013)
- [Unseen Object Instance Segmentation for Robotic Environments](https://mlsanity.com/paper/2007.08073/) (2020)
- [Learning Affordance Landscapes for Interaction Exploration in 3D Environments](https://mlsanity.com/paper/2008.09241/) (2020)
- [KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations](https://mlsanity.com/paper/2002.12687/) (2020)
- [Learning to See before Learning to Act: Visual Pre-training for Manipulation](https://mlsanity.com/paper/2107.00646/) (2021)
- [Broadly-Exploring, Local-Policy Trees for Long-Horizon Task Planning](https://mlsanity.com/paper/2010.06491/) (2020)
- [Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning](https://mlsanity.com/paper/2005.10872/) (2020)
- [Visual Affordance and Function Understanding: A Survey](https://mlsanity.com/paper/1807.06775/) (2018)
- [Composing Pick-and-Place Tasks By Grounding Language](https://mlsanity.com/paper/2102.08094/) (2021)
- [Adversarial Skill Networks: Unsupervised Robot Skill Learning from Video](https://mlsanity.com/paper/1910.09430/) (2019)
- [Learning Object Placements For Relational Instructions by Hallucinating Scene Representations](https://mlsanity.com/paper/2001.08481/) (2020)
- [Self-supervised 3D Shape and Viewpoint Estimation from Single Images for Robotics](https://mlsanity.com/paper/1910.07948/) (2019)

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

- [Visual Language Maps for Robot Navigation](https://mlsanity.com/paper/2210.05714/) (2022)
- [What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Data](https://mlsanity.com/paper/2204.06252/) (2022)
- [Large Language Models for Robotics: A Survey](https://mlsanity.com/paper/2311.07226/) (2023)
- [Grounding Language with Visual Affordances over Unstructured Data](https://mlsanity.com/paper/2210.01911/) (2022)
- [Latent Plans for Task-Agnostic Offline Reinforcement Learning](https://mlsanity.com/paper/2209.08959/) (2022)
- [End-to-End Affordance Learning for Robotic Manipulation](https://mlsanity.com/paper/2209.12941/) (2022)
- [Training Strategies for Efficient Embodied Reasoning](https://mlsanity.com/paper/2505.08243/) (2025)
- [One-Shot Open Affordance Learning with Foundation Models](https://mlsanity.com/paper/2311.17776/) (2023)
- [Vision-Language Models Provide Promptable Representations for Reinforcement Learning](https://mlsanity.com/paper/2402.02651/) (2024)
- [One-Shot Transfer of Affordance Regions? AffCorrs!](https://mlsanity.com/paper/2209.07147/) (2022)
- [Universal Visual Decomposer: Long-Horizon Manipulation Made Easy](https://mlsanity.com/paper/2310.08581/) (2023)
- [UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulation](https://mlsanity.com/paper/2506.09284/) (2025)
- [Language-Conditioned Imitation Learning with Base Skill Priors under Unstructured Data](https://mlsanity.com/paper/2305.19075/) (2023)
- [Empowering Large Language Models on Robotic Manipulation with Affordance Prompting](https://mlsanity.com/paper/2404.11027/) (2024)
- [On the Effectiveness of Retrieval, Alignment, and Replay in Manipulation](https://mlsanity.com/paper/2312.12345/) (2023)
- [Scaling Robot Policy Learning via Zero-Shot Labeling with Foundation Models](https://mlsanity.com/paper/2410.17772/) (2024)
- [ManiFoundation Model for General-Purpose Robotic Manipulation of Contact Synthesis with Arbitrary Objects and Robots](https://mlsanity.com/paper/2405.06964/) (2024)
- [Recent Advances of Deep Robotic Affordance Learning: A Reinforcement Learning Perspective](https://mlsanity.com/paper/2303.05344/) (2023)
- [Visual-Policy Learning through Multi-Camera View to Single-Camera View Knowledge Distillation for Robot Manipulation Tasks](https://mlsanity.com/paper/2303.07026/) (2023)
- [AffordanceSAM: Segment Anything Once More in Affordance Grounding](https://mlsanity.com/paper/2504.15650/) (2025)
- [Information-driven Affordance Discovery for Efficient Robotic Manipulation](https://mlsanity.com/paper/2405.03865/) (2024)
- [O3Afford: One-Shot 3D Object-to-Object Affordance Grounding for Generalizable Robotic Manipulation](https://mlsanity.com/paper/2509.06233/) (2025)
- [Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning](https://mlsanity.com/paper/2602.08167/) (2026)
- [From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data](https://mlsanity.com/paper/2606.00054/) (2026)
- [Multi-Object Graph Affordance Network: Goal-Oriented Planning through Learned Compound Object Affordances](https://mlsanity.com/paper/2309.10426/) (2023)
- [Robot Self-Improvement via Human-Video Dynamics Models](https://mlsanity.com/paper/2606.21406/) (2026)
- [DORA: Object Affordance-Guided Reinforcement Learning for Dexterous Robotic Manipulation](https://mlsanity.com/paper/2505.14819/) (2025)
- [Manipulate-to-Navigate: Reinforcement Learning with Visual Affordances and Manipulability Priors](https://mlsanity.com/paper/2508.13151/) (2025)
- [GMT: Goal-Conditioned Multimodal Transformer for 6-DOF Object Trajectory Synthesis in 3D Scenes](https://mlsanity.com/paper/2603.17993/) (2026)
- [Cognitive Manipulation: Semi-supervised Visual Representation and Classroom-to-real Reinforcement Learning for Assembly in Semi-structured Environments](https://mlsanity.com/paper/2406.00364/) (2024)

## Abstract (arXiv)

Robots operating in human-centered environments should have the ability to understand how objects function: what can be done with each object, where this interaction may occur, and how the object is used to achieve a goal. To this end, we propose a novel approach that extracts a self-supervised visual affordance model from human teleoperated play data and leverages it to enable efficient policy learning and motion planning. We combine model-based planning with model-free deep reinforcement learning (RL) to learn policies that favor the same object regions favored by people, while requiring minimal robot interactions with the environment. We evaluate our algorithm, Visual Affordance-guided Policy Optimization (VAPO), with both diverse simulation manipulation tasks and real world robot tidy-up experiments to demonstrate the effectiveness of our affordance-guided policies. We find that our policies train 4x faster than the baselines and generalize better to novel objects because our visual affordance model can anticipate their affordance regions.