mlsanityData to 7 Oct 2026

Eliciting Compatible Demonstrations for Multi-Human Imitation Learning

arXiv 2210.08073 ↗First posted 14 Oct 2022cs.RO cs.AI cs.HCcited by 22

On the map: Offline RL and imitation learning from data → Robot manipulation imitation learning

Abstract (arXiv)

Imitation learning from human-provided demonstrations is a strong approach for learning policies for robot manipulation. While the ideal dataset for imitation learning is homogenous and low-variance -- reflecting a single, optimal method for performing a task -- natural human behavior has a great deal of heterogeneity, with several optimal ways to demonstrate a task. This multimodality is inconsequential to human users, with task variations manifesting as subconscious choices; for example, reaching down, then across to grasp an object, versus reaching across, then down. Yet, this mismatch presents a problem for interactive imitation learning, where sequences of users improve on a policy by iteratively collecting new, possibly conflicting demonstrations. To combat this problem of demonstrator incompatibility, this work designs an approach for 1) measuring the compatibility of a new demonstration given a base policy, and 2) actively eliciting more compatible demonstrations from new users. Across two simulation tasks requiring long-horizon, dexterous manipulation and a real-world "food plating" task with a Franka Emika Panda arm, we show that we can both identify incompatible demonstrations via post-hoc filtering, and apply our compatibility measure to actively elicit compatible demonstrations from new users, leading to improved task success rates across simulated and real environments.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 30 of its 43 references that are in the map. First posted on arXiv 14 Oct 2022.

Builds on

30 of 43 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning4 Feb
  2. 2021Bottom-Up Skill Discovery from Unsegmented Demonstrations for Long-Horizon Robot Manipulation28 Sep
  3. 2021LazyDAgger: Reducing Context Switching in Interactive Imitation Learning31 Mar

Other references · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016Layer Normalizationcited by 5,579
  4. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  5. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  6. 2019Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learningcited by 750
  7. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 699
  8. 2021Implicit Behavioral Cloningcited by 442
  9. 2020Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamicscited by 423
  10. 2019Learning Latent Plans from Playcited by 310
  11. 2020Critic Regularized Regressioncited by 269
  12. 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 256
15 more
  1. 2021Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasetscited by 248
  2. 2018HG-DAgger: Interactive Imitation Learning with Human Expertscited by 245
  3. 2021RvS: What is Essential for Offline RL via Supervised Learning?cited by 184
  4. 2021ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learningcited by 98
  5. 2018EnsembleDAgger: A Bayesian Approach to Safe Imitation Learningcited by 96
  6. 2020Learning from Suboptimal Demonstration via Self-Supervised Reward Regressioncited by 84
  7. 2016Query-Efficient Imitation Learning for End-to-End Autonomous Drivingcited by 83
  8. 2017Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Netscited by 64
  9. 2021Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answeringcited by 62
  10. 2022Imitation Learning by Estimating Expertise of Demonstratorscited by 50
  11. 2021Confidence-Aware Imitation Learning from Demonstrations with Varying Optimalitycited by 44
  12. 2021Learning Multimodal Rewards from Rankingscited by 41
  13. 2021TRAIL: Near-Optimal Imitation Learning with Suboptimal Datacited by 39
  14. 2017Burn-In Demonstrations for Multi-Modal Imitation Learningcited by 9
  15. 2021A Closer Look at Advantage-Filtered Behavioral Cloning in High-Noise Datasetscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 6; 2024: 5; 2025: 6; 2026: 4.

22 papers.

Sort:

By area:

  1. 2022Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deploymentcited by 101
  2. 2023Data Quality in Imitation Learningcited by 72
  3. 2023Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasetscited by 56
  4. 2023HYDRA: Hybrid Robot Actions for Imitation Learningcited by 54
  5. 2024Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Samplingcited by 46
  6. 2024Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learningcited by 44
  7. 2025CUPID: Curating Data your Robot Loves with Influence Functionscited by 21
  8. 2024So You Think You Can Scale Up Autonomous Robot Data Collection?cited by 17
  9. 2023Learning to Discern: Imitating Heterogeneous Human Demonstrations with Preference and Representation Learningcited by 14
  10. 2025How to Train Your Robots? The Impact of Demonstration Modality on Imitation Learningcited by 11
  11. 2025Guiding Data Collection via Factored Scaling Curvescited by 10
  12. 2025SCIZOR: A Self-Supervised Approach to Data Curation for Large-Scale Imitation Learningcited by 9
10 more
  1. 2024Consistency Matters: Defining Demonstration Data Quality Metrics in Robot Learning from Demonstrationcited by 6
  2. 2023Generating Language Corrections for Teaching Physical Control Taskscited by 4
  3. 2023IIFL: Implicit Interactive Fleet Learning from Heterogeneous Human Supervisorscited by 4
  4. 2024DIDA: Denoised Imitation Learning based on Domain Adaptationcited by 2
  5. 2025Counterfactual Behavior Cloning: Offline Imitation Learning from Imperfect Human Demonstrationscited by 2
  6. 2026ATHENA: Accelerated Multi-Task Heterogeneous Influence Functions for Robot Data Curationcited by 1
  7. 2026Behavior Uncloning: Distilling Mode Redirection into Policy Weights without Inference-Time Steeringcited by 1
  8. 2025Going Beyond Expert Performance via Deep Implicit Imitation Reinforcement Learningcited by 0
  9. 2026Improving Robotic Imitation Learning via Trajectory Standardizationcited by 0
  10. 2026Imperfection for Precision: Upcycling Imperfect Data for High-Precision Robotic Manipulationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Human-to-Robot Interaction: Learning from Video Demonstration for Robot Imitation
  2. 2025Learning a Thousand Tasks in a Day
  3. 2024VITAL: Interactive Few-Shot Imitation Learning via Visual Human-in-the-Loop Corrections
  4. 2024Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations
  5. 2026Difference-Aware Retrieval Policies for Imitation Learning
  6. 2023MimicPlay: Long-Horizon Imitation Learning by Watching Human Play
  7. 2021Coarse-to-Fine Imitation Learning: Robot Manipulation from a Single Demonstration
  8. 2021Imitation Learning: Progress, Taxonomies and Challenges