mlsanityData to 7 Oct 2026

Semi-Supervised One-Shot Imitation Learning

arXiv 2408.05285 ↗First posted 9 Aug 2024cs.LG cs.AIcited by 0

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

One-shot Imitation Learning~(OSIL) aims to imbue AI agents with the ability to learn a new task from a single demonstration. To supervise the learning, OSIL typically requires a prohibitively large number of paired expert demonstrations -- i.e. trajectories corresponding to different variations of the same semantic task. To overcome this limitation, we introduce the semi-supervised OSIL problem setting, where the learning agent is presented with a large dataset of trajectories with no task labels (i.e. an unpaired dataset), along with a small dataset of multiple demonstrations per semantic task (i.e. a paired dataset). This presents a more realistic and practical embodiment of few-shot learning and requires the agent to effectively leverage weak supervision from a large dataset of trajectories. Subsequently, we develop an algorithm specifically applicable to this semi-supervised OSIL setting. Our approach first learns an embedding space where different tasks cluster uniquely. We utilize this embedding space and the clustering it supports to self-generate pairings between trajectories in the large unpaired dataset. Through empirical results on simulated control tasks, we demonstrate that OSIL models trained on such self-generated pairings are competitive with OSIL models trained with ground-truth labels, presenting a major advancement in the label-efficiency of OSIL.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 38 of its 51 references that are in the map. First posted on arXiv 9 Aug 2024.

Builds on

38 of 51 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021Visual Adversarial Imitation Learning using Variational Models16 Jul

Other references · 37

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  6. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  7. 2016Matching Networks for One Shot Learningcited by 2,246
  8. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
  9. 2016Generative Adversarial Imitation Learningcited by 1,576
  10. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,406
  11. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  12. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
25 more
  1. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,173
  2. 2018Diversity is All You Need: Learning Skills without a Reward Functioncited by 734
  3. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
  4. 2019Meta-Learning with Implicit Gradientscited by 523
  5. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 517
  6. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 485
  7. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  8. 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 400
  9. 2019Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learningcited by 380
  10. 2020dm_control: Software and Tasks for Continuous Controlcited by 368
  11. 2019Learning Latent Plans from Playcited by 310
  12. 2017One-Shot Imitation Learningcited by 232
  13. 2017One-Shot Visual Imitation Learning via Meta-Learningcited by 225
  14. 2021APS: Active Pretraining with Successor Featurescited by 109
  15. 2020Transformers for One-Shot Visual Imitationcited by 77
  16. 2018Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definitioncited by 66
  17. 2018Task-Embedded Control Networks for Few-Shot Imitation Learningcited by 65
  18. 2022How to Leverage Unlabeled Data in Offline Reinforcement Learningcited by 61
  19. 2019Meta-Learning via Learned Losscited by 60
  20. 2020Model-Based Inverse Reinforcement Learning from Visual Demonstrationscited by 52
  21. 2019Meta-Inverse Reinforcement Learning with Probabilistic Context Variablescited by 50
  22. 2021Towards More Generalizable One-shot Visual Imitation Learningcited by 48
  23. 2023Masked Trajectory Models for Prediction, Representation, and Controlcited by 40
  24. 2021Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classificationcited by 38
  25. 2020Pseudo-Representation Labeling Semi-Supervised Learningcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Self-evolved Imitation Learning in Simulated World
  2. 2026Semi-Supervised Cross-Domain Imitation Learning
  3. 2023CEIL: Generalized Contextual Imitation Learning
  4. 2023Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasets
  5. 2024One-shot Imitation in a Non-Stationary Environment via Multi-Modal Skill
  6. 2026On the Sample Efficiency of Inverse Dynamics Models for Semi-Supervised Imitation Learning
  7. 2025ManiLong-Shot: Interaction-Aware One-Shot Imitation Learning for Long-Horizon Manipulation
  8. 2025SCIZOR: A Self-Supervised Approach to Data Curation for Large-Scale Imitation Learning