# Cross-Domain Transfer via Semantic Skill Imitation

arXiv: https://arxiv.org/abs/2212.07407 · HTML: https://mlsanity.com/paper/2212.07407/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 40 references that are in the map.
- First posted on arXiv 14 Dec 2022.

## Builds on (most cited first, 30 of 32)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [Rescaling Egocentric Vision](https://mlsanity.com/paper/2006.13256/) (2020)
- [Time-Contrastive Networks: Self-Supervised Learning from Video](https://mlsanity.com/paper/1704.06888/) (2017)
- [Data-Efficient Hierarchical Reinforcement Learning](https://mlsanity.com/paper/1805.08296/) (2018)
- [The Option-Critic Architecture](https://mlsanity.com/paper/1609.05140/) (2016)
- [Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning](https://mlsanity.com/paper/1910.11956/) (2019)
- [Overcoming Exploration in Reinforcement Learning with Demonstrations](https://mlsanity.com/paper/1709.10089/) (2017)
- [Learning Agile Robotic Locomotion Skills by Imitating Animals](https://mlsanity.com/paper/2004.00784/) (2020)
- [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)
- [RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation](https://mlsanity.com/paper/1811.02790/) (2018)
- [OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning](https://mlsanity.com/paper/2010.13611/) (2020)
- [DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills](https://mlsanity.com/paper/1804.02717/) (2018)
- [One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning](https://mlsanity.com/paper/1802.01557/) (2018)
- [Reinforcement and Imitation Learning for Diverse Visuomotor Skills](https://mlsanity.com/paper/1802.09564/) (2018)
- [Learning Generalizable Robotic Reward Functions from "In-The-Wild" Human Videos](https://mlsanity.com/paper/2103.16817/) (2021)
- [Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control](https://mlsanity.com/paper/1811.01848/) (2018)
- [AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos](https://mlsanity.com/paper/1912.04443/) (2019)
- [Reinforcement Learning with Videos: Combining Offline Observations with Interaction](https://mlsanity.com/paper/2011.06507/) (2020)
- [Neural Task Programming: Learning to Generalize Across Hierarchical Tasks](https://mlsanity.com/paper/1710.01813/) (2017)
- [Multiple Interactions Made Easy (MIME): Large Scale Demonstrations Data for Imitation](https://mlsanity.com/paper/1810.07121/) (2018)
- [Demonstration-Guided Reinforcement Learning with Learned Skills](https://mlsanity.com/paper/2107.10253/) (2021)
- [Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller](https://mlsanity.com/paper/1911.09676/) (2019)
- [Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration](https://mlsanity.com/paper/1807.03480/) (2018)
- [Model-Based Inverse Reinforcement Learning from Visual Demonstrations](https://mlsanity.com/paper/2010.09034/) (2020)

## Built on by (most cited first, 18 of 18)

- [PlayFusion: Skill Acquisition via Diffusion from Language-Annotated Play](https://mlsanity.com/paper/2312.04549/) (2023)
- [Towards Generalist Robot Learning from Internet Video: A Survey](https://mlsanity.com/paper/2404.19664/) (2024)
- [Legs as Manipulator: Pushing Quadrupedal Agility Beyond Locomotion](https://mlsanity.com/paper/2303.11330/) (2023)
- [UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations](https://mlsanity.com/paper/2505.08787/) (2025)
- [ZeroMimic: Distilling Robotic Manipulation Skills from Web Videos](https://mlsanity.com/paper/2503.23877/) (2025)
- [Bridging the Human to Robot Dexterity Gap through Object-Oriented Rewards](https://mlsanity.com/paper/2410.23289/) (2024)
- [A Comprehensive Survey of Cross-Domain Policy Transfer for Embodied Agents](https://mlsanity.com/paper/2402.04580/) (2024)
- [Learning by Watching: A Review of Video-based Learning Approaches for Robot Manipulation](https://mlsanity.com/paper/2402.07127/) (2024)
- [xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editing](https://mlsanity.com/paper/2409.08687/) (2024)
- [One-shot Imitation in a Non-Stationary Environment via Multi-Modal Skill](https://mlsanity.com/paper/2402.08369/) (2024)
- [Chain-of-Goals Hierarchical Policy for Long-Horizon Offline Goal-Conditioned RL](https://mlsanity.com/paper/2602.03389/) (2026)
- [Robot Learning from Human Videos: A Survey](https://mlsanity.com/paper/2604.27621/) (2026)
- [Dynamic Contrastive Skill Learning with State-Transition Based Skill Clustering and Dynamic Length Adjustment](https://mlsanity.com/paper/2504.14805/) (2025)
- [SemTra: A Semantic Skill Translator for Cross-Domain Zero-Shot Policy Adaptation](https://mlsanity.com/paper/2402.07418/) (2024)
- [In-Context Policy Adaptation via Cross-Domain Skill Diffusion](https://mlsanity.com/paper/2509.04535/) (2025)
- [Semi-Supervised Cross-Domain Imitation Learning](https://mlsanity.com/paper/2602.10793/) (2026)
- [Offline Policy Learning via Skill-step Abstraction for Long-horizon Goal-Conditioned Tasks](https://mlsanity.com/paper/2408.11300/) (2024)
- [Robot Policy Transfer with Online Demonstrations: An Active Reinforcement Learning Approach](https://mlsanity.com/paper/2503.12993/) (2025)

## Abstract (arXiv)

We propose an approach for semantic imitation, which uses demonstrations from a source domain, e.g. human videos, to accelerate reinforcement learning (RL) in a different target domain, e.g. a robotic manipulator in a simulated kitchen. Instead of imitating low-level actions like joint velocities, our approach imitates the sequence of demonstrated semantic skills like "opening the microwave" or "turning on the stove". This allows us to transfer demonstrations across environments (e.g. real-world to simulated kitchen) and agent embodiments (e.g. bimanual human demonstration to robotic arm). We evaluate on three challenging cross-domain learning problems and match the performance of demonstration-accelerated RL approaches that require in-domain demonstrations. In a simulated kitchen environment, our approach learns long-horizon robot manipulation tasks, using less than 3 minutes of human video demonstrations from a real-world kitchen. This enables scaling robot learning via the reuse of demonstrations, e.g. collected as human videos, for learning in any number of target domains.