# Learning Reward Functions for Robotic Manipulation by Observing Humans

arXiv: https://arxiv.org/abs/2211.09019 · HTML: https://mlsanity.com/paper/2211.09019/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 47 references that are in the map.
- First posted on arXiv 16 Nov 2022.

## Builds on (most cited first, 30 of 40)

- [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)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction](https://mlsanity.com/paper/1906.00949/) (2019)
- [Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1910.00177/) (2019)
- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [Behavior Regularized Offline Reinforcement Learning](https://mlsanity.com/paper/1911.11361/) (2019)
- [BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning](https://mlsanity.com/paper/2202.02005/) (2022)
- [Behavioral Cloning from Observation](https://mlsanity.com/paper/1805.01954/) (2018)
- [Time-Contrastive Networks: Self-Supervised Learning from Video](https://mlsanity.com/paper/1704.06888/) (2017)
- [VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training](https://mlsanity.com/paper/2210.00030/) (2022)
- [Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection](https://mlsanity.com/paper/1603.02199/) (2016)
- [Critic Regularized Regression](https://mlsanity.com/paper/2006.15134/) (2020)
- [Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets](https://mlsanity.com/paper/2109.13396/) (2021)
- [Streaming End-to-end Speech Recognition For Mobile Devices](https://mlsanity.com/paper/1811.06621/) (2018)
- [DexMV: Imitation Learning for Dexterous Manipulation from Human Videos](https://mlsanity.com/paper/2108.05877/) (2021)
- [Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning](https://mlsanity.com/paper/1809.02925/) (2018)
- [One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning](https://mlsanity.com/paper/1802.01557/) (2018)
- [Learning Generalizable Robotic Reward Functions from "In-The-Wild" Human Videos](https://mlsanity.com/paper/2103.16817/) (2021)

## Built on by (most cited first, 17 of 17)

- [Diffusion Reward: Learning Rewards via Conditional Video Diffusion](https://mlsanity.com/paper/2312.14134/) (2023)
- [ViViDex: Learning Vision-based Dexterous Manipulation from Human Videos](https://mlsanity.com/paper/2404.15709/) (2024)
- [Rank2Reward: Learning Shaped Reward Functions from Passive Video](https://mlsanity.com/paper/2404.14735/) (2024)
- [Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data](https://mlsanity.com/paper/2306.03346/) (2023)
- [Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics](https://mlsanity.com/paper/2405.19988/) (2024)
- [PROGRESSOR: A Perceptually Guided Reward Estimator with Self-Supervised Online Refinement](https://mlsanity.com/paper/2411.17764/) (2024)
- [Human-oriented Representation Learning for Robotic Manipulation](https://mlsanity.com/paper/2310.03023/) (2023)
- [VIEW: Visual Imitation Learning with Waypoints](https://mlsanity.com/paper/2404.17906/) (2024)
- [Giving Robots a Hand: Learning Generalizable Manipulation with Eye-in-Hand Human Video Demonstrations](https://mlsanity.com/paper/2307.05959/) (2023)
- [The Duality of Generative AI and Reinforcement Learning in Robotics: A Review](https://mlsanity.com/paper/2410.16411/) (2024)
- [Adaptive Articulated Object Manipulation On The Fly with Foundation Model Reasoning and Part Grounding](https://mlsanity.com/paper/2507.18276/) (2025)
- [Reinforcement Learning from Wild Animal Videos](https://mlsanity.com/paper/2412.04273/) (2024)
- [Dexterous Manipulation Based on Prior Dexterous Grasp Pose Knowledge](https://mlsanity.com/paper/2412.15587/) (2024)
- [Inductive Learning of Robot Task Knowledge from Raw Data and Online Expert Feedback](https://mlsanity.com/paper/2501.07507/) (2025)
- [PANDORA: Diffusion Policy Learning for Dexterous Robotic Piano Playing](https://mlsanity.com/paper/2503.14545/) (2025)
- [GORDON: Graph-based Object-centric Rewards for Decomposition of Long-Horizon Manipulation](https://mlsanity.com/paper/2608.03753/) (2026)
- [Disentangling Task-Relevant Latent Dynamics for Reward Modeling](https://mlsanity.com/paper/2610.14159/) (2026)

## Abstract (arXiv)

Observing a human demonstrator manipulate objects provides a rich, scalable and inexpensive source of data for learning robotic policies. However, transferring skills from human videos to a robotic manipulator poses several challenges, not least a difference in action and observation spaces. In this work, we use unlabeled videos of humans solving a wide range of manipulation tasks to learn a task-agnostic reward function for robotic manipulation policies. Thanks to the diversity of this training data, the learned reward function sufficiently generalizes to image observations from a previously unseen robot embodiment and environment to provide a meaningful prior for directed exploration in reinforcement learning. We propose two methods for scoring states relative to a goal image: through direct temporal regression, and through distances in an embedding space obtained with time-contrastive learning. By conditioning the function on a goal image, we are able to reuse one model across a variety of tasks. Unlike prior work on leveraging human videos to teach robots, our method, Human Offline Learned Distances (HOLD) requires neither a priori data from the robot environment, nor a set of task-specific human demonstrations, nor a predefined notion of correspondence across morphologies, yet it is able to accelerate training of several manipulation tasks on a simulated robot arm compared to using only a sparse reward obtained from task completion.