InterPReT: Interactive Policy Restructuring and Training Enable Effective Imitation Learning from Laypersons
On the map: Offline RL and imitation learning from data → Imitation learning methods
Abstract (arXiv)
Imitation learning has shown success in many tasks by learning from expert demonstrations. However, most existing work relies on large-scale demonstrations from technical professionals and close monitoring of the training process. These are challenging for a layperson when they want to teach the agent new skills. To lower the barrier of teaching AI agents, we propose Interactive Policy Restructuring and Training (InterPReT), which takes user instructions to continually update the policy structure and optimize its parameters to fit user demonstrations. This enables end-users to interactively give instructions and demonstrations, monitor the agent's performance, and review the agent's decision-making strategies. A user study (N=34) on teaching an AI agent to drive in a racing game confirms that our approach yields more robust policies without impairing system usability, compared to a generic imitation learning baseline, when a layperson is responsible for both giving demonstrations and determining when to stop. This shows that our method is more suitable for end-users without much technical background in machine learning to train a dependable policy
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 39 of its 77 references that are in the map. First posted on arXiv 4 Feb 2026.
Builds on
39 of 77 references.
Closest ancestors · 6
Same direction, newest first
- 2025Sample-Efficient Behavior Cloning Using General Domain Knowledge27 Jan
- 2021Hyperparameter Selection for Imitation Learning25 May
- 2021Learning from Imperfect Demonstrations from Agents with Varying Dynamics10 Mar
- 2019Causal Confusion in Imitation Learning28 May
- 2019Imitation Learning from Imperfect Demonstration27 Jan
- 2018An Algorithmic Perspective on Imitation Learning16 Nov
Other references · 33
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
- 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
- 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,258
- 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
- 2022A Survey on In-context Learningcited by 717
- 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 377
- 2024Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robotscited by 373
- 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 288
- 2020Language Conditioned Imitation Learning over Unstructured Datacited by 208
- 2023GELLO: A General, Low-Cost, and Intuitive Teleoperation Framework for Robot Manipulatorscited by 180
21 more
- 2024RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedbackcited by 147
- 2024ALOHA Unleashed: A Simple Recipe for Robot Dexteritycited by 128
- 2024Yell At Your Robot: Improving On-the-Fly from Language Correctionscited by 123
- 2024The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performancecited by 97
- 2023Anchor3DLane: Learning to Regress 3D Anchors for Monocular 3D Lane Detectioncited by 48
- 2024RACER: Rich Language-Guided Failure Recovery Policies for Imitation Learningcited by 46
- 2025RaC: Robot Learning for Long-Horizon Tasks by Scaling Recovery and Correctioncited by 35
- 2023StudentEval: A Benchmark of Student-Written Prompts for Large Language Models of Codecited by 32
- 2025FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learningcited by 31
- 2025What Matters in Learning from Large-Scale Datasets for Robot Manipulationcited by 20
- 2022Using Both Demonstrations and Language Instructions to Efficiently Learn Robotic Taskscited by 17
- 2024Human-Agent Joint Learning for Efficient Robot Manipulation Skill Acquisitioncited by 10
- 2023Programming-by-Demonstration for Long-Horizon Robot Taskscited by 9
- 2024Language Guided Exploration for RL Agents in Text Environmentscited by 9
- 2024Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Inputcited by 8
- 2024ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Roboticscited by 8
- 2022WebRobot: Web Robotic Process Automation using Interactive Programming-by-Demonstrationcited by 7
- 2023PDSketch: Integrated Planning Domain Programming and Learningcited by 7
- 2024Can Large Language Models Help Developers with Robotic Finite State Machine Modification?cited by 5
- 2025Second-order Theory of Mind for Human Teachers and Robot Learnerscited by 2
- 2025Interactive Program Synthesis for Modeling Collaborative Physical Activities from Narrated Demonstrationscited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2025Evaluating Interpretable Reinforcement Learning by Distilling Policies into Programs
- 2026When Does On-Policy Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning
- 2024Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model
- 2025Structured Imitation Learning of Interactive Policies through Inverse Games
- 2024Online Adaptation for Enhancing Imitation Learning Policies
- 2020Interactive Imitation Learning in State-Space
- 2025Steering Robots with Inference-Time Interactions
- 2024Don't Start from Scratch: Behavioral Refinement via Interpolant-based Policy Diffusion