FlowRetrieval: Flow-Guided Data Retrieval for Few-Shot Imitation Learning

• URL: http://arxiv.org/abs/2408.16944v2
• Date: Fri, 11 Oct 2024 07:17:42 GMT
• Title: FlowRetrieval: Flow-Guided Data Retrieval for Few-Shot Imitation Learning
• Authors: Li-Heng Lin, Yuchen Cui, Amber Xie, Tianyu Hua, Dorsa Sadigh,
• Abstract summary: Few-shot imitation learning relies on only a small amount of task-specific demonstrations to efficiently adapt a policy for a given downstream tasks. We propose FlowRetrieval, an approach that leverages optical flow representations for both extracting similar motions to target tasks from prior data. Our results show FlowRetrieval significantly outperforms prior methods across simulated and real-world domains.
• Score: 28.523528119584526
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Few-shot imitation learning relies on only a small amount of task-specific demonstrations to efficiently adapt a policy for a given downstream tasks. Retrieval-based methods come with a promise of retrieving relevant past experiences to augment this target data when learning policies. However, existing data retrieval methods fall under two extremes: they either rely on the existence of exact behaviors with visually similar scenes in the prior data, which is impractical to assume; or they retrieve based on semantic similarity of high-level language descriptions of the task, which might not be that informative about the shared low-level behaviors or motions across tasks that is often a more important factor for retrieving relevant data for policy learning. In this work, we investigate how we can leverage motion similarity in the vast amount of cross-task data to improve few-shot imitation learning of the target task. Our key insight is that motion-similar data carries rich information about the effects of actions and object interactions that can be leveraged during few-shot adaptation. We propose FlowRetrieval, an approach that leverages optical flow representations for both extracting similar motions to target tasks from prior data, and for guiding learning of a policy that can maximally benefit from such data. Our results show FlowRetrieval significantly outperforms prior methods across simulated and real-world domains, achieving on average 27% higher success rate than the best retrieval-based prior method. In the Pen-in-Cup task with a real Franka Emika robot, FlowRetrieval achieves 3.7x the performance of the baseline imitation learning technique that learns from all prior and target data. Website: https://flow-retrieval.github.io

Related papers

• ALP: Action-Aware Embodied Learning for Perception [60.64801970249279]
  We introduce Action-Aware Embodied Learning for Perception (ALP) ALP incorporates action information into representation learning through a combination of optimizing a reinforcement learning policy and an inverse dynamics prediction objective. We show that ALP outperforms existing baselines in several downstream perception tasks.
  arXiv  Detail & Related papers  (2023-06-16T21:51:04Z)
• Behavior Retrieval: Few-Shot Imitation Learning by Querying Unlabeled Datasets [73.2096288987301]
  We propose a simple approach that uses a small amount of downstream expert data to selectively query relevant behaviors from an offline, unlabeled dataset. We observe that our method learns to query only the relevant transitions to the task, filtering out sub-optimal or task-irrelevant data. Our simple querying approach outperforms more complex goal-conditioned methods by 20% across simulated and real robotic manipulation tasks from images.
  arXiv  Detail & Related papers  (2023-04-18T05:42:53Z)
• Reinforcement Learning from Passive Data via Latent Intentions [86.4969514480008]
  We show that passive data can still be used to learn features that accelerate downstream RL. Our approach learns from passive data by modeling intentions. Our experiments demonstrate the ability to learn from many forms of passive data, including cross-embodiment video data and YouTube videos.
  arXiv  Detail & Related papers  (2023-04-10T17:59:05Z)
• Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information [100.03188187735624]
  We introduce a novel approach based on PLMs and pointwise V-information (PVI), a metric that can measure the usefulness of a datapoint for training a model. Our method first fine-tunes a PLM on a small seed of training data and then synthesizes new datapoints - utterances that correspond to given intents. Our method is thus able to leverage the expressive power of large language models to produce diverse training data.
  arXiv  Detail & Related papers  (2023-02-10T07:37:49Z)
• An Exploration of Data Efficiency in Intra-Dataset Task Transfer for Dialog Understanding [65.75873687351553]
  This study explores the effects of varying quantities of target task training data on sequential transfer learning in the dialog domain. Unintuitively, our data shows that often target task training data size has minimal effect on how sequential transfer learning performs compared to the same model without transfer learning.
  arXiv  Detail & Related papers  (2022-10-21T04:36:46Z)
• A Memory-Related Multi-Task Method Based on Task-Agnostic Exploration [26.17597857264231]
  In contrast to imitation learning, there is no expert data, only the data collected through environmental exploration. Since the action sequence to solve the new task may be the combination of trajectory segments of multiple training tasks, the test task and the solving strategy do not exist directly in the training data. We propose a Memory-related Multi-task Method (M3) to address this problem.
  arXiv  Detail & Related papers  (2022-09-09T03:02:49Z)
• Self-Supervised Human Activity Recognition with Localized Time-Frequency Contrastive Representation Learning [16.457778420360537]
  We propose a self-supervised learning solution for human activity recognition with smartphone accelerometer data. We develop a model that learns strong representations from accelerometer signals, while reducing the model's reliance on class labels. We evaluate the performance of the proposed solution on three datasets, namely MotionSense, HAPT, and HHAR.
  arXiv  Detail & Related papers  (2022-08-26T22:47:18Z)
• Efficient Self-Supervised Data Collection for Offline Robot Learning [17.461103383630853]
  A practical approach to robot reinforcement learning is to first collect a large batch of real or simulated robot interaction data. We develop a simple-yet-effective goal-conditioned reinforcement-learning method that actively focuses data collection on novel observations.
  arXiv  Detail & Related papers  (2021-05-10T18:42:58Z)
• Probabilistic Active Meta-Learning [15.432006404678981]
  We introduce task selection based on prior experience into a meta-learning algorithm. We provide empirical evidence that our approach improves data-efficiency when compared to strong baselines on simulated robotic experiments.
  arXiv  Detail & Related papers  (2020-07-17T12:51:42Z)
• Meta-Reinforcement Learning Robust to Distributional Shift via Model Identification and Experience Relabeling [126.69933134648541]
  We present a meta-reinforcement learning algorithm that is both efficient and extrapolates well when faced with out-of-distribution tasks at test time. Our method is based on a simple insight: we recognize that dynamics models can be adapted efficiently and consistently with off-policy data.
  arXiv  Detail & Related papers  (2020-06-12T13:34:46Z)

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.