Understanding the World Through Action

• URL: http://arxiv.org/abs/2110.12543v1
• Date: Sun, 24 Oct 2021 22:33:52 GMT
• Title: Understanding the World Through Action
• Authors: Sergey Levine
• Abstract summary: I will argue that a general, principled, and powerful framework for utilizing unlabeled data can be derived from reinforcement learning. I will discuss how such a procedure is more closely aligned with potential downstream tasks.
• Score: 91.3755431537592
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The recent history of machine learning research has taught us that machine learning methods can be most effective when they are provided with very large, high-capacity models, and trained on very large and diverse datasets. This has spurred the community to search for ways to remove any bottlenecks to scale. Often the foremost among such bottlenecks is the need for human effort, including the effort of curating and labeling datasets. As a result, considerable attention in recent years has been devoted to utilizing unlabeled data, which can be collected in vast quantities. However, some of the most widely used methods for training on such unlabeled data themselves require human-designed objective functions that must correlate in some meaningful way to downstream tasks. I will argue that a general, principled, and powerful framework for utilizing unlabeled data can be derived from reinforcement learning, using general purpose unsupervised or self-supervised reinforcement learning objectives in concert with offline reinforcement learning methods that can leverage large datasets. I will discuss how such a procedure is more closely aligned with potential downstream tasks, and how it could build on existing techniques that have been developed in recent years.

Related papers

• Granularity Matters in Long-Tail Learning [62.30734737735273]
  We offer a novel perspective on long-tail learning, inspired by an observation: datasets with finer granularity tend to be less affected by data imbalance. We introduce open-set auxiliary classes that are visually similar to existing ones, aiming to enhance representation learning for both head and tail classes. To prevent the overwhelming presence of auxiliary classes from disrupting training, we introduce a neighbor-silencing loss.
  arXiv  Detail & Related papers  (2024-10-21T13:06:21Z)
• Deep Active Learning for Data Mining from Conflict Text Corpora [0.0]
  This paper proposes one such approach that is inexpensive and high performance, leveraging active learning. The approach shows performance similar to human (gold-standard) coding while reducing the amount of required human annotation by as much as 99%.
  arXiv  Detail & Related papers  (2024-02-02T17:16:23Z)
• A Survey of Label-Efficient Deep Learning for 3D Point Clouds [109.07889215814589]
  This paper presents the first comprehensive survey of label-efficient learning of point clouds. We propose a taxonomy that organizes label-efficient learning methods based on the data prerequisites provided by different types of labels. For each approach, we outline the problem setup and provide an extensive literature review that showcases relevant progress and challenges.
  arXiv  Detail & Related papers  (2023-05-31T12:54:51Z)
• 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)
• Diverse Complexity Measures for Dataset Curation in Self-driving [80.55417232642124]
  We propose a new data selection method that exploits a diverse set of criteria that quantize interestingness of traffic scenes. Our experiments show that the proposed curation pipeline is able to select datasets that lead to better generalization and higher performance.
  arXiv  Detail & Related papers  (2021-01-16T23:45:02Z)
• Active learning for object detection in high-resolution satellite images [1.6500749121196985]
  This study aims at reviewing the most relevant active learning techniques to be used for object detection on very high resolution imagery. It shows an example of the value of such techniques on a relevant operational use case: aircraft detection.
  arXiv  Detail & Related papers  (2021-01-07T10:57:38Z)
• The Emerging Trends of Multi-Label Learning [45.63795570392158]
  Exabytes of data are generated daily by humans, leading to the growing need for new efforts in dealing with the grand challenges for multi-label learning brought by big data. There is a lack of systemic studies that focus explicitly on analyzing the emerging trends and new challenges of multi-label learning in the era of big data. It is imperative to call for a comprehensive survey to fulfill this mission and delineate future research directions and new applications.
  arXiv  Detail & Related papers  (2020-11-23T03:36:00Z)
• 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)
• Sense and Learn: Self-Supervision for Omnipresent Sensors [9.442811508809994]
  We present a framework named Sense and Learn for representation or feature learning from raw sensory data. It consists of several auxiliary tasks that can learn high-level and broadly useful features entirely from unannotated data without any human involvement in the tedious labeling process. Our methodology achieves results that are competitive with the supervised approaches and close the gap through fine-tuning a network while learning the downstream tasks in most cases.
  arXiv  Detail & Related papers  (2020-09-28T11:57:43Z)
• An Overview of Deep Semi-Supervised Learning [8.894935073145252]
  There is a rising research interest in semi-supervised learning and its applications to deep neural networks. This paper provides a comprehensive overview of deep semi-supervised learning, starting with an introduction to the field.
  arXiv  Detail & Related papers  (2020-06-09T14:08:03Z)

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.