Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation

• URL: http://arxiv.org/abs/2508.06426v1
• Date: Fri, 08 Aug 2025 16:14:01 GMT
• Title: Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation
• Authors: Youguang Xing, Xu Luo, Junlin Xie, Lianli Gao, Hengtao Shen, Jingkuan Song,
• Abstract summary: Generalist robot policies trained on large-scale datasets such as Open X-Embodiment (OXE) demonstrate strong performance across a wide range of tasks.<n>They often struggle to generalize beyond the distribution of their training data.<n>We identify shortcut learning as a key impediment to generalization.
• Score: 117.54237701533805
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generalist robot policies trained on large-scale datasets such as Open X-Embodiment (OXE) demonstrate strong performance across a wide range of tasks. However, they often struggle to generalize beyond the distribution of their training data. In this paper, we investigate the underlying cause of this limited generalization capability. We identify shortcut learning -- the reliance on task-irrelevant features -- as a key impediment to generalization. Through comprehensive theoretical and empirical analysis, we uncover two primary contributors to shortcut learning: (1) limited diversity within individual sub-datasets, and (2) significant distributional disparities across sub-datasets, leading to dataset fragmentation. These issues arise from the inherent structure of large-scale datasets like OXE, which are typically composed of multiple sub-datasets collected independently across varied environments and embodiments. Our findings provide critical insights into dataset collection strategies that can reduce shortcut learning and enhance the generalization ability of generalist robot policies. Moreover, in scenarios where acquiring new large-scale data is impractical, we demonstrate that carefully selected robotic data augmentation strategies can effectively reduce shortcut learning in existing offline datasets, thereby improving generalization capabilities of generalist robot policies, e.g., $\pi_0$, in both simulation and real-world environments. More information at https://lucky-light-sun.github.io/proj/shortcut-learning-in-grps/.

Related papers

• Query-Based Adaptive Aggregation for Multi-Dataset Joint Training Toward Universal Visual Place Recognition [10.8843105310375]
  Query-based Adaptive Aggregation (QAA) is a novel feature aggregation technique that leverages learned queries as reference codebooks.<n>We show that QAA outperforms state-of-the-art models, achieving balanced generalization across diverse datasets while maintaining peak performance comparable to dataset-specific models.
  arXiv  Detail & Related papers  (2025-07-04T22:40:03Z)
• What Matters in Learning from Large-Scale Datasets for Robot Manipulation [12.703188997313223]
  We conduct a large-scale dataset composition study to answer this question.<n>We develop a data generation framework to procedurally emulate common sources of diversity in existing datasets.<n>We find that camera poses and spatial arrangements are crucial dimensions for both diversity in collection and alignment in retrieval.
  arXiv  Detail & Related papers  (2025-06-16T14:25:29Z)
• 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)
• Efficient Data Collection for Robotic Manipulation via Compositional Generalization [70.76782930312746]
  We show that policies can compose environmental factors from their data to succeed when encountering unseen factor combinations. We propose better in-domain data collection strategies that exploit composition. We provide videos at http://iliad.stanford.edu/robot-data-comp/.
  arXiv  Detail & Related papers  (2024-03-08T07:15:38Z)
• Leveraging sparse and shared feature activations for disentangled representation learning [112.22699167017471]
  We propose to leverage knowledge extracted from a diversified set of supervised tasks to learn a common disentangled representation. We validate our approach on six real world distribution shift benchmarks, and different data modalities.
  arXiv  Detail & Related papers  (2023-04-17T01:33:24Z)
• Generalization with Lossy Affordances: Leveraging Broad Offline Data for Learning Visuomotor Tasks [65.23947618404046]
  We introduce a framework that acquires goal-conditioned policies for unseen temporally extended tasks via offline reinforcement learning on broad data. When faced with a novel task goal, the framework uses an affordance model to plan a sequence of lossy representations as subgoals that decomposes the original task into easier problems. We show that our framework can be pre-trained on large-scale datasets of robot experiences from prior work and efficiently fine-tuned for novel tasks, entirely from visual inputs without any manual reward engineering.
  arXiv  Detail & Related papers  (2022-10-12T21:46:38Z)
• A Survey of Learning on Small Data: Generalization, Optimization, and Challenge [101.27154181792567]
  Learning on small data that approximates the generalization ability of big data is one of the ultimate purposes of AI. This survey follows the active sampling theory under a PAC framework to analyze the generalization error and label complexity of learning on small data. Multiple data applications that may benefit from efficient small data representation are surveyed.
  arXiv  Detail & Related papers  (2022-07-29T02:34:19Z)
• Exploiting Shared Representations for Personalized Federated Learning [54.65133770989836]
  We propose a novel federated learning framework and algorithm for learning a shared data representation across clients and unique local heads for each client. Our algorithm harnesses the distributed computational power across clients to perform many local-updates with respect to the low-dimensional local parameters for every update of the representation. This result is of interest beyond federated learning to a broad class of problems in which we aim to learn a shared low-dimensional representation among data distributions.
  arXiv  Detail & Related papers  (2021-02-14T05:36:25Z)
• 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)
• Few-Shot Unsupervised Continual Learning through Meta-Examples [21.954394608030388]
  We introduce a novel and complex setting involving unsupervised meta-continual learning with unbalanced tasks. We exploit a meta-learning scheme that simultaneously alleviates catastrophic forgetting and favors the generalization to new tasks. Experimental results on few-shot learning benchmarks show competitive performance even compared to the supervised case.
  arXiv  Detail & Related papers  (2020-09-17T07:02:07Z)

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.