Semi-Supervised One-Shot Imitation Learning

• URL: http://arxiv.org/abs/2408.05285v1
• Date: Fri, 9 Aug 2024 18:11:26 GMT
• Title: Semi-Supervised One-Shot Imitation Learning
• Authors: Philipp Wu, Kourosh Hakhamaneshi, Yuqing Du, Igor Mordatch, Aravind Rajeswaran, Pieter Abbeel,
• Abstract summary: One-shot Imitation Learning aims to imbue AI agents with the ability to learn a new task from a single demonstration. We introduce the semi-supervised OSIL problem setting, where the learning agent is presented with a large dataset of trajectories. We develop an algorithm specifically applicable to this semi-supervised OSIL setting.
• Score: 83.94646047695412
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: One-shot Imitation Learning~(OSIL) aims to imbue AI agents with the ability to learn a new task from a single demonstration. To supervise the learning, OSIL typically requires a prohibitively large number of paired expert demonstrations -- i.e. trajectories corresponding to different variations of the same semantic task. To overcome this limitation, we introduce the semi-supervised OSIL problem setting, where the learning agent is presented with a large dataset of trajectories with no task labels (i.e. an unpaired dataset), along with a small dataset of multiple demonstrations per semantic task (i.e. a paired dataset). This presents a more realistic and practical embodiment of few-shot learning and requires the agent to effectively leverage weak supervision from a large dataset of trajectories. Subsequently, we develop an algorithm specifically applicable to this semi-supervised OSIL setting. Our approach first learns an embedding space where different tasks cluster uniquely. We utilize this embedding space and the clustering it supports to self-generate pairings between trajectories in the large unpaired dataset. Through empirical results on simulated control tasks, we demonstrate that OSIL models trained on such self-generated pairings are competitive with OSIL models trained with ground-truth labels, presenting a major advancement in the label-efficiency of OSIL.

Related papers

• Incremental Self-training for Semi-supervised Learning [56.57057576885672]
  IST is simple yet effective and fits existing self-training-based semi-supervised learning methods. We verify the proposed IST on five datasets and two types of backbone, effectively improving the recognition accuracy and learning speed.
  arXiv  Detail & Related papers  (2024-04-14T05:02:00Z)
• Data-CUBE: Data Curriculum for Instruction-based Sentence Representation Learning [85.66907881270785]
  We propose a data curriculum method, namely Data-CUBE, that arranges the orders of all the multi-task data for training. In the task level, we aim to find the optimal task order to minimize the total cross-task interference risk. In the instance level, we measure the difficulty of all instances per task, then divide them into the easy-to-difficult mini-batches for training.
  arXiv  Detail & Related papers  (2024-01-07T18:12:20Z)
• GenCo: An Auxiliary Generator from Contrastive Learning for Enhanced Few-Shot Learning in Remote Sensing [9.504503675097137]
  We introduce a generator-based contrastive learning framework (GenCo) that pre-trains backbones and simultaneously explores variants of feature samples. In fine-tuning, the auxiliary generator can be used to enrich limited labeled data samples in feature space. We demonstrate the effectiveness of our method in improving few-shot learning performance on two key remote sensing datasets.
  arXiv  Detail & Related papers  (2023-07-27T03:59:19Z)
• Coreset Sampling from Open-Set for Fine-Grained Self-Supervised Learning [10.57079240576682]
  We introduce a novel Open-Set Self-Supervised Learning problem under the assumption that a large-scale unlabeled open-set is available. In our problem setup, it is crucial to consider the distribution mismatch between the open-set and target dataset. We demonstrate that SimCore significantly improves representation learning performance through extensive experimental settings.
  arXiv  Detail & Related papers  (2023-03-20T13:38:29Z)
• Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task Distributions [8.88133567816717]
  We name this problem as Semi-supervised meta-learning with Evolving Task diStributions, abbreviated as SETS. We propose an OOD Robust and knowleDge presErved semi-supeRvised meta-learning approach (ORDER) to tackle these two major challenges. Specifically, our ORDER introduces a novel mutual information regularization to robustify the model with unlabeled OOD data and adopts an optimal transport regularization to remember previously learned knowledge in feature space.
  arXiv  Detail & Related papers  (2022-09-03T21:22:14Z)
• Continual Barlow Twins: continual self-supervised learning for remote sensing semantic segmentation [8.775728170359024]
  We propose a new algorithm for merging Self-Supervised Learning (SSL) and Continual Learning (CL) for remote sensing applications, that we call Continual Barlow Twins (CBT) CBT combines the advantages of one of the simplest self-supervision techniques, i.e., Barlow Twins, with the Elastic Weight Consolidation method to avoid catastrophic forgetting. For the first time we evaluate SSL methods on a highly heterogeneous Earth Observation dataset, showing the effectiveness of these strategies.
  arXiv  Detail & Related papers  (2022-05-23T14:02:12Z)
• Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning [101.28281124670647]
  Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data. We propose a novel training mechanism that could effectively exploit the presence of OOD data for enhanced feature learning. Our approach substantially lifts the performance on open-set SSL and outperforms the state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2021-08-12T09:14:44Z)
• Lifelong Learning Without a Task Oracle [13.331659934508764]
  Supervised deep neural networks are known to undergo a sharp decline in the accuracy of older tasks when new tasks are learned. We propose and compare several candidate task-assigning mappers which require very little memory overhead. Best-performing variants only impose an average cost of 1.7% parameter memory increase.
  arXiv  Detail & Related papers  (2020-11-09T21:30:31Z)
• DAGA: Data Augmentation with a Generation Approach for Low-resource Tagging Tasks [88.62288327934499]
  We propose a novel augmentation method with language models trained on the linearized labeled sentences. Our method is applicable to both supervised and semi-supervised settings.
  arXiv  Detail & Related papers  (2020-11-03T07:49:15Z)
• Learning to Count in the Crowd from Limited Labeled Data [109.2954525909007]
  We focus on reducing the annotation efforts by learning to count in the crowd from limited number of labeled samples. Specifically, we propose a Gaussian Process-based iterative learning mechanism that involves estimation of pseudo-ground truth for the unlabeled data.
  arXiv  Detail & Related papers  (2020-07-07T04:17:01Z)

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.