Data to 14 Oct 2026

One-Shot Visual Imitation Learning via Meta-Learning

arXiv 1709.04905 ↗First posted 14 Sep 2017cs.LG cs.AI cs.CVcited by 228

Not on the map. Why?

Cited by 113 in Offline RL and imitation learning from data, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In order for a robot to be a generalist that can perform a wide range of jobs, it must be able to acquire a wide variety of skills quickly and efficiently in complex unstructured environments. High-capacity models such as deep neural networks can enable a robot to represent complex skills, but learning each skill from scratch then becomes infeasible. In this work, we present a meta-imitation learning method that enables a robot to learn how to learn more efficiently, allowing it to acquire new skills from just a single demonstration. Unlike prior methods for one-shot imitation, our method can scale to raw pixel inputs and requires data from significantly fewer prior tasks for effective learning of new skills. Our experiments on both simulated and real robot platforms demonstrate the ability to learn new tasks, end-to-end, from a single visual demonstration.

Key facts. Cited by 228 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Sep 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 6; 2019: 14; 2020: 10; 2021: 35; 2022: 31; 2023: 42; 2024: 50; 2025: 29; 2026: 11.

228 papers.

Sort:

By area:

2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 725
2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 523
2018An Algorithmic Perspective on Imitation Learningcited by 459
2022VIMA: General Robot Manipulation with Multimodal Promptscited by 407
2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 391
2021Transformers Can Do Bayesian Inferencecited by 360
2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 327
2025X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Modelcited by 303
2021Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasetscited by 250
2021MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scalecited by 229
2023MimicPlay: Long-Horizon Imitation Learning by Watching Human Playcited by 223

38 more

2021How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learnedcited by 213
2023RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shotcited by 183
2024EgoMimic: Scaling Imitation Learning via Egocentric Videocited by 175
2022Human-to-Robot Imitation in the Wildcited by 161
2024DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulationcited by 160
2024Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulationcited by 153
2022Prompting Decision Transformer for Few-Shot Policy Generalizationcited by 146
2018Reinforcement and Imitation Learning for Diverse Visuomotor Skillscited by 126
2024Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulationcited by 124
2021Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotationcited by 118
2024DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learningcited by 116
2021ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learningcited by 108
2021Generalized Decision Transformer for Offline Hindsight Information Matchingcited by 106
2023Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysiscited by 103
2022Instruction-driven history-aware policies for robotic manipulationscited by 94
2019Recent Advances in Imitation Learning from Observationcited by 93
2020Offline Meta-Reinforcement Learning with Advantage Weightingcited by 93
2021Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstrationcited by 93
2024Vision Language Models are In-Context Value Learnerscited by 90
2022DexVIP: Learning Dexterous Grasping with Human Hand Pose Priors from Videocited by 89
2022You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstrationcited by 81
2023XSkill: Cross Embodiment Skill Discoverycited by 75
2024EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learningcited by 75
2024Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Roboticscited by 73
20243D-ViTac: Learning Fine-Grained Manipulation with Visuo-Tactile Sensingcited by 72
2022CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation Learningcited by 71
2023SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Executioncited by 70
2024In-Context Imitation Learning via Next-Token Predictioncited by 70
2023Imitating Task and Motion Planning with Visuomotor Transformerscited by 66
2023Advances and Challenges in Meta-Learning: A Technical Reviewcited by 65
2023Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasetscited by 58
2024RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulationcited by 58
2024Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstructioncited by 54
2023Towards Generalizable Zero-Shot Manipulation via Translating Human Interaction Planscited by 52
2024SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deploymentcited by 52
2023Zero-Shot Robot Manipulation from Passive Human Videoscited by 51
2019Meta-Inverse Reinforcement Learning with Probabilistic Context Variablescited by 50
2020Deep Imitation Learning for Bimanual Robotic Manipulationcited by 50

50 most cited of 228 All 228 (JSON)