# Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations

arXiv: https://arxiv.org/abs/2303.01497 · HTML: https://mlsanity.com/paper/2303.01497/

## Key facts

- Cited by 75 papers in the map (data through 14 Oct 2026).
- Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 54 of its 80 references that are in the map.
- First posted on arXiv 2 Mar 2023.

## Placed in

- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Builds on (most cited first, 30 of 54)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [What Matters in Learning from Offline Human Demonstrations for Robot Manipulation](https://mlsanity.com/paper/2108.03298/) (2021)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [AWAC: Accelerating Online Reinforcement Learning with Offline Datasets](https://mlsanity.com/paper/2006.09359/) (2020)
- [Behavioral Cloning from Observation](https://mlsanity.com/paper/1805.01954/) (2018)
- [Learning Robust Rewards with Adversarial Inverse Reinforcement Learning](https://mlsanity.com/paper/1710.11248/) (2017)
- [Implicit Behavioral Cloning](https://mlsanity.com/paper/2109.00137/) (2021)
- [Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning](https://mlsanity.com/paper/2107.09645/) (2021)
- [Exploring the Limitations of Behavior Cloning for Autonomous Driving](https://mlsanity.com/paper/1904.08980/) (2019)
- [Overcoming Exploration in Reinforcement Learning with Demonstrations](https://mlsanity.com/paper/1709.10089/) (2017)
- [Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation](https://mlsanity.com/paper/1811.10092/) (2018)
- [Behavior Transformers: Cloning k modes with one stone](https://mlsanity.com/paper/2206.11251/) (2022)
- [Residual Reinforcement Learning for Robot Control](https://mlsanity.com/paper/1812.03201/) (2018)
- [Soft-DTW: a Differentiable Loss Function for Time-Series](https://mlsanity.com/paper/1703.01541/) (2017)
- [Learning Agile Robotic Locomotion Skills by Imitating Animals](https://mlsanity.com/paper/2004.00784/) (2020)
- [Masked Visual Pre-training for Motor Control](https://mlsanity.com/paper/2203.06173/) (2022)
- [Real-World Robot Learning with Masked Visual Pre-training](https://mlsanity.com/paper/2210.03109/) (2022)
- [Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning](https://mlsanity.com/paper/1809.02925/) (2018)
- [Generative Adversarial Imitation from Observation](https://mlsanity.com/paper/1807.06158/) (2018)
- [Residual Policy Learning](https://mlsanity.com/paper/1812.06298/) (2018)
- [The Surprising Effectiveness of Representation Learning for Visual Imitation](https://mlsanity.com/paper/2112.01511/) (2021)
- [Primal Wasserstein Imitation Learning](https://mlsanity.com/paper/2006.04678/) (2020)
- [Jump-Start Reinforcement Learning](https://mlsanity.com/paper/2204.02372/) (2022)
- [Visual Imitation Made Easy](https://mlsanity.com/paper/2008.04899/) (2020)
- [From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data](https://mlsanity.com/paper/2210.10047/) (2022)

## Built on by (most cited first, 30 of 75)

- [Diffusion Policy Policy Optimization](https://mlsanity.com/paper/2409.00588/) (2024)
- [RoboCLIP: One Demonstration is Enough to Learn Robot Policies](https://mlsanity.com/paper/2310.07899/) (2023)
- [ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills](https://mlsanity.com/paper/2502.01143/) (2025)
- [3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations](https://mlsanity.com/paper/2403.03954/) (2024)
- [On Bringing Robots Home](https://mlsanity.com/paper/2311.16098/) (2023)
- [From Imitation to Refinement -- Residual RL for Precise Assembly](https://mlsanity.com/paper/2407.16677/) (2024)
- [DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping](https://mlsanity.com/paper/2502.20900/) (2025)
- [Bunny-VisionPro: Real-Time Bimanual Dexterous Teleoperation for Imitation Learning](https://mlsanity.com/paper/2407.03162/) (2024)
- [Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model](https://mlsanity.com/paper/2412.13630/) (2024)
- [Residual Off-Policy RL for Finetuning Behavior Cloning Policies](https://mlsanity.com/paper/2509.19301/) (2025)
- [Vision-based Manipulation from Single Human Video with Open-World Object Graphs](https://mlsanity.com/paper/2405.20321/) (2024)
- [DINOBot: Robot Manipulation via Retrieval and Alignment with Vision Foundation Models](https://mlsanity.com/paper/2402.13181/) (2024)
- [An Unbiased Look at Datasets for Visuo-Motor Pre-Training](https://mlsanity.com/paper/2310.09289/) (2023)
- [ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learning](https://mlsanity.com/paper/2510.05070/) (2025)
- [AffordDP: Generalizable Diffusion Policy with Transferable Affordance](https://mlsanity.com/paper/2412.03142/) (2024)
- [3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model](https://mlsanity.com/paper/2506.06199/) (2025)
- [See to Touch: Learning Tactile Dexterity through Visual Incentives](https://mlsanity.com/paper/2309.12300/) (2023)
- [MimicTouch: Leveraging Multi-modal Human Tactile Demonstrations for Contact-rich Manipulation](https://mlsanity.com/paper/2310.16917/) (2023)
- [Adaptive Mobile Manipulation for Articulated Objects In the Open World](https://mlsanity.com/paper/2401.14403/) (2024)
- [Compliant Residual DAgger: Improving Real-World Contact-Rich Manipulation with Human Corrections](https://mlsanity.com/paper/2506.16685/) (2025)
- [Bridging the Human to Robot Dexterity Gap through Object-Oriented Rewards](https://mlsanity.com/paper/2410.23289/) (2024)
- [Lessons from Learning to Spin "Pens"](https://mlsanity.com/paper/2407.18902/) (2024)
- [RoboCopilot: Human-in-the-loop Interactive Imitation Learning for Robot Manipulation](https://mlsanity.com/paper/2503.07771/) (2025)
- [IntervenGen: Interventional Data Generation for Robust and Data-Efficient Robot Imitation Learning](https://mlsanity.com/paper/2405.01472/) (2024)
- [One-Shot Imitation Learning: A Pose Estimation Perspective](https://mlsanity.com/paper/2310.12077/) (2023)
- [Dexterous Manipulation through Imitation Learning: A Survey](https://mlsanity.com/paper/2504.03515/) (2025)
- [Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own](https://mlsanity.com/paper/2310.02635/) (2023)
- [CordViP: Correspondence-based Visuomotor Policy for Dexterous Manipulation in Real-World](https://mlsanity.com/paper/2502.08449/) (2025)
- [A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search](https://mlsanity.com/paper/2506.05294/) (2025)
- [Composing Pre-Trained Object-Centric Representations for Robotics From "What" and "Where" Foundation Models](https://mlsanity.com/paper/2404.13474/) (2024)

## Abstract (arXiv)

While imitation learning provides us with an efficient toolkit to train robots, learning skills that are robust to environment variations remains a significant challenge. Current approaches address this challenge by relying either on large amounts of demonstrations that span environment variations or on handcrafted reward functions that require state estimates. Both directions are not scalable to fast imitation. In this work, we present Fast Imitation of Skills from Humans (FISH), a new imitation learning approach that can learn robust visual skills with less than a minute of human demonstrations. Given a weak base-policy trained by offline imitation of demonstrations, FISH computes rewards that correspond to the "match" between the robot's behavior and the demonstrations. These rewards are then used to adaptively update a residual policy that adds on to the base-policy. Across all tasks, FISH requires at most twenty minutes of interactive learning to imitate demonstrations on object configurations that were not seen in the demonstrations. Importantly, FISH is constructed to be versatile, which allows it to be used across robot morphologies (e.g. xArm, Allegro, Stretch) and camera configurations (e.g. third-person, eye-in-hand). Our experimental evaluations on 9 different tasks show that FISH achieves an average success rate of 93%, which is around 3.8x higher than prior state-of-the-art methods.