Beyond the Majority: Long-tail Imitation Learning for Robotic Manipulation

• URL: http://arxiv.org/abs/2602.06512v1
• Date: Fri, 06 Feb 2026 09:10:02 GMT
• Title: Beyond the Majority: Long-tail Imitation Learning for Robotic Manipulation
• Abstract summary: Long-tail distribution of training demonstrations hinders policy learning.<n>Approaching-Phase Augmentation (APA) transfers knowledge from data-rich head tasks to data-scarce tail tasks without requiring demonstrations.
• Score: 121.31598641762251
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While generalist robot policies hold significant promise for learning diverse manipulation skills through imitation, their performance is often hindered by the long-tail distribution of training demonstrations. Policies learned on such data, which is heavily skewed towards a few data-rich head tasks, frequently exhibit poor generalization when confronted with the vast number of data-scarce tail tasks. In this work, we conduct a comprehensive analysis of the pervasive long-tail challenge inherent in policy learning. Our analysis begins by demonstrating the inefficacy of conventional long-tail learning strategies (e.g., re-sampling) for improving the policy's performance on tail tasks. We then uncover the underlying mechanism for this failure, revealing that data scarcity on tail tasks directly impairs the policy's spatial reasoning capability. To overcome this, we introduce Approaching-Phase Augmentation (APA), a simple yet effective scheme that transfers knowledge from data-rich head tasks to data-scarce tail tasks without requiring external demonstrations. Extensive experiments in both simulation and real-world manipulation tasks demonstrate the effectiveness of APA. Our code and demos are publicly available at: https://mldxy.github.io/Project-VLA-long-tail/.

Related papers

• Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement Learning [21.705096559151286]
  We show that offline reinforcement learning can be used to harness non-expert data to enhance the performance of imitation learning policies.<n>Our approach shows that broadening the support of the policy distribution can allow imitation algorithms augmented by offline RL to solve tasks robustly.
  arXiv  Detail & Related papers  (2025-10-22T11:43:39Z)
• Data-Efficient Multitask DAgger [15.497645748861913]
  Generalist robot policies that can perform many tasks typically require extensive expert data or simulations for training.<n>We propose a novel Data-Efficient multitask DAgger framework that distills a single multitask policy from multiple task-specific expert policies.
  arXiv  Detail & Related papers  (2025-09-29T20:17:35Z)
• Reinforcement Learning via Implicit Imitation Guidance [49.88208134736617]
  A natural approach is to incorporate an imitation learning objective, either as regularization during training or to acquire a reference policy.<n>We propose to use prior data solely for guiding exploration via noise added to the policy, sidestepping the need for explicit behavior cloning constraints.<n>Our approach achieves up to 2-3x improvement over prior reinforcement learning from offline methods across seven simulated continuous control tasks.
  arXiv  Detail & Related papers  (2025-06-09T07:32:52Z)
• Object-Focus Actor for Data-efficient Robot Generalization Dexterous Manipulation [14.977743061489518]
  We introduce Object-Focus Actor (OFA), a novel, data-efficient approach for generalized dexterous manipulation.<n>OFA exploits the consistent end trajectories observed in dexterous manipulation tasks, allowing for efficient policy training.<n>OFA achieves robust performance with only 10 demonstrations, highlighting its data efficiency.
  arXiv  Detail & Related papers  (2025-05-21T04:37:56Z)
• STRAP: Robot Sub-Trajectory Retrieval for Augmented Policy Learning [8.860366821983211]
  STRAP is a technique for leveraging pre-trained vision foundation models and dynamic time warping to retrieve sub-sequences of trajectories from large training corpora in a robust fashion.<n>This work proposes STRAP, a technique for leveraging pre-trained vision foundation models and dynamic time warping to retrieve sub-sequences of trajectories from large training corpora in a robust fashion.
  arXiv  Detail & Related papers  (2024-12-19T18:54:06Z)
• Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning [17.092640837991883]
  Reinforcement learning (RL) presents a promising framework to learn policies through environment interaction. One direction includes augmenting RL with offline data demonstrating desired tasks, but past work often require a lot of high-quality demonstration data. We show how the combination of a reverse curriculum and forward curriculum in our method, RFCL, enables significant improvements in demonstration and sample efficiency.
  arXiv  Detail & Related papers  (2024-05-06T11:33:12Z)
• Hierarchical Few-Shot Imitation with Skill Transition Models [66.81252581083199]
  Few-shot Imitation with Skill Transition Models (FIST) is an algorithm that extracts skills from offline data and utilizes them to generalize to unseen tasks. We show that FIST is capable of generalizing to new tasks and substantially outperforms prior baselines in navigation experiments.
  arXiv  Detail & Related papers  (2021-07-19T15:56:01Z)
• A Framework for Efficient Robotic Manipulation [79.10407063260473]
  We show that a single robotic arm can learn sparse-reward manipulation policies from pixels. We show that, given only 10 demonstrations, a single robotic arm can learn sparse-reward manipulation policies from pixels.
  arXiv  Detail & Related papers  (2020-12-14T22:18:39Z)
• Parrot: Data-Driven Behavioral Priors for Reinforcement Learning [79.32403825036792]
  We propose a method for pre-training behavioral priors that can capture complex input-output relationships observed in successful trials. We show how this learned prior can be used for rapidly learning new tasks without impeding the RL agent's ability to try out novel behaviors.
  arXiv  Detail & Related papers  (2020-11-19T18:47:40Z)
• COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning [78.13740204156858]
  We show that we can reuse prior data to extend new skills simply through dynamic programming. We demonstrate the effectiveness of our approach by chaining together several behaviors seen in prior datasets for solving a new task. We train our policies in an end-to-end fashion, mapping high-dimensional image observations to low-level robot control commands.
  arXiv  Detail & Related papers  (2020-10-27T17:57:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.