mlsanityData to 14 Oct 2026

BEAC: Imitating Complex Exploration and Task-oriented Behaviors for Invisible Object Nonprehensile Manipulation

arXiv 2503.16803 ↗First posted 21 Mar 2025cs.RO cs.LGcited by 0

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

Abstract (arXiv)

Applying imitation learning (IL) is challenging to nonprehensile manipulation tasks of invisible objects with partial observations, such as excavating buried rocks. The demonstrator must make such complex action decisions as exploring to find the object and task-oriented actions to complete the task while estimating its hidden state, perhaps causing inconsistent action demonstration and high cognitive load problems. For these problems, work in human cognitive science suggests that promoting the use of pre-designed, simple exploration rules for the demonstrator may alleviate the problems of action inconsistency and high cognitive load. Therefore, when performing imitation learning from demonstrations using such exploration rules, it is important to accurately imitate not only the demonstrator's task-oriented behavior but also his/her mode-switching behavior (exploratory or task-oriented behavior) under partial observation. Based on the above considerations, this paper proposes a novel imitation learning framework called Belief Exploration-Action Cloning (BEAC), which has a switching policy structure between a pre-designed exploration policy and a task-oriented action policy trained on the estimated belief states based on past history. In simulation and real robot experiments, we confirmed that our proposed method achieved the best task performance, higher mode and action prediction accuracies, while reducing the cognitive load in the demonstration indicated by a user study.

Key facts. No citing papers in the map yet (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 21 of its 51 references that are in the map. First posted on arXiv 21 Mar 2025.

Builds on

21 of 51 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Bi-ACT: Bilateral Control-Based Imitation Learning via Action Chunking with Transformer31 Jan

Other references · 20

  1. 2019On Variational Bounds of Mutual Informationcited by 559
  2. 2018An Algorithmic Perspective on Imitation Learningcited by 459
  3. 2015A Recurrent Latent Variable Model for Sequential Datacited by 362
  4. 2017Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperationcited by 289
  5. 2019VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learningcited by 217
  6. 2023A Survey of Imitation Learning: Algorithms, Recent Developments, and Challengescited by 148
  7. 2018Deep Variational Reinforcement Learning for POMDPscited by 125
  8. 2021ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learningcited by 108
  9. 2022Partially Observable Markov Decision Processes in Robotics: A Surveycited by 86
  10. 2022Deep Transformer Q-Networks for Partially Observable Reinforcement Learningcited by 36
  11. 2023HACMan: Learning Hybrid Actor-Critic Maps for 6D Non-Prehensile Manipulationcited by 29
  12. 2019Learning Belief Representations for Imitation Learning in POMDPscited by 24
8 more
  1. 2018Learning to Grasp Without Seeingcited by 19
  2. 2019A Deep Learning Approach to Grasping the Invisiblecited by 19
  3. 2022Disturbance-Injected Robust Imitation Learning with Task Achievementcited by 9
  4. 2021Bayesian Disturbance Injection: Robust Imitation Learning of Flexible Policiescited by 6
  5. 2022Soft Tracking Using Contacts for Cluttered Objects to Perform Blind Object Retrievalcited by 5
  6. 2023Disturbance Injection under Partial Automation: Robust Imitation Learning for Long-horizon Taskscited by 4
  7. 2016Imitation Learning with Recurrent Neural Networkscited by 2
  8. 2024Progressive-Resolution Policy Distillation: Leveraging Coarse-Resolution Simulations for Time-Efficient Fine-Resolution Policy Learningcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Diffusion Model-Augmented Behavioral Cloning
  2. 2018Zero-Shot Visual Imitation
  3. 2025Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration
  4. 2024Zero-shot Imitation Policy via Search in Demonstration Dataset
  5. 2025Improving Generalization Ability of Robotic Imitation Learning by Resolving Causal Confusion in Observations
  6. 2025A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search
  7. 2021Manipulator-Independent Representations for Visual Imitation
  8. 2024FoAM: Foresight-Augmented Multi-Task Imitation Policy for Robotic Manipulation