Learning Representations for Pixel-based Control: What Matters and Why?
- URL: http://arxiv.org/abs/2111.07775v1
- Date: Mon, 15 Nov 2021 14:16:28 GMT
- Title: Learning Representations for Pixel-based Control: What Matters and Why?
- Authors: Manan Tomar, Utkarsh A. Mishra, Amy Zhang, Matthew E. Taylor
- Abstract summary: We present a simple baseline approach that can learn meaningful representations with no metric-based learning, no data augmentations, no world-model learning, and no contrastive learning.
Our results show that finer categorization of benchmarks on the basis of characteristics like density of reward, planning horizon of the problem, presence of task-irrelevant components, etc., is crucial in evaluating algorithms.
- Score: 22.177382138487566
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Learning representations for pixel-based control has garnered significant
attention recently in reinforcement learning. A wide range of methods have been
proposed to enable efficient learning, leading to sample complexities similar
to those in the full state setting. However, moving beyond carefully curated
pixel data sets (centered crop, appropriate lighting, clear background, etc.)
remains challenging. In this paper, we adopt a more difficult setting,
incorporating background distractors, as a first step towards addressing this
challenge. We present a simple baseline approach that can learn meaningful
representations with no metric-based learning, no data augmentations, no
world-model learning, and no contrastive learning. We then analyze when and why
previously proposed methods are likely to fail or reduce to the same
performance as the baseline in this harder setting and why we should think
carefully about extending such methods beyond the well curated environments.
Our results show that finer categorization of benchmarks on the basis of
characteristics like density of reward, planning horizon of the problem,
presence of task-irrelevant components, etc., is crucial in evaluating
algorithms. Based on these observations, we propose different metrics to
consider when evaluating an algorithm on benchmark tasks. We hope such a
data-centric view can motivate researchers to rethink representation learning
when investigating how to best apply RL to real-world tasks.
Related papers
- Robust compressive tracking via online weighted multiple instance learning [0.6813925418351435]
We propose a visual object tracking algorithm by integrating a coarse-to-fine search strategy based on sparse representation and the weighted multiple instance learning (WMIL) algorithm.
Compared with the other trackers, our approach has more information of the original signal with less complexity due to the coarse-to-fine search method, and also has weights for important samples.
arXiv Detail & Related papers (2024-06-14T10:48:17Z) - Clustering-based Domain-Incremental Learning [4.835091081509403]
Key challenge in continual learning is the so-called "catastrophic forgetting problem"
We propose an online clustering-based approach on a dynamically updated finite pool of samples or gradients.
We demonstrate the effectiveness of the proposed strategy and its promising performance compared to state-of-the-art methods.
arXiv Detail & Related papers (2023-09-21T13:49:05Z) - Accelerating exploration and representation learning with offline
pre-training [52.6912479800592]
We show that exploration and representation learning can be improved by separately learning two different models from a single offline dataset.
We show that learning a state representation using noise-contrastive estimation and a model of auxiliary reward can significantly improve the sample efficiency on the challenging NetHack benchmark.
arXiv Detail & Related papers (2023-03-31T18:03:30Z) - What Makes Good Contrastive Learning on Small-Scale Wearable-based
Tasks? [59.51457877578138]
We study contrastive learning on the wearable-based activity recognition task.
This paper presents an open-source PyTorch library textttCL-HAR, which can serve as a practical tool for researchers.
arXiv Detail & Related papers (2022-02-12T06:10:15Z) - Point Discriminative Learning for Unsupervised Representation Learning
on 3D Point Clouds [54.31515001741987]
We propose a point discriminative learning method for unsupervised representation learning on 3D point clouds.
We achieve this by imposing a novel point discrimination loss on the middle level and global level point features.
Our method learns powerful representations and achieves new state-of-the-art performance.
arXiv Detail & Related papers (2021-08-04T15:11:48Z) - A survey of active learning algorithms for supervised remote sensing
image classification [5.384800591054857]
Defining an efficient training set is one of the most delicate phases for the success of remote sensing image classification routines.
Active learning aims at building efficient training sets by iteratively improving the model performance through sampling.
This paper reviews and tests the main families of active learning algorithms: committee, large margin and posterior probability-based.
arXiv Detail & Related papers (2021-04-15T21:36:59Z) - Low-Regret Active learning [64.36270166907788]
We develop an online learning algorithm for identifying unlabeled data points that are most informative for training.
At the core of our work is an efficient algorithm for sleeping experts that is tailored to achieve low regret on predictable (easy) instances.
arXiv Detail & Related papers (2021-04-06T22:53:45Z) - Weakly Supervised Representation Learning with Coarse Labels [29.67549798642795]
Deep learning can learn discriminative patterns from raw materials directly in a task-dependent manner.
For some real-world applications, it is too expensive to collect the task-specific labels, such as visual search in online shopping.
We propose an algorithm to learn the fine-grained patterns for the target task, when only its coarse-class labels are available.
arXiv Detail & Related papers (2020-05-19T18:05:20Z) - Distilling Localization for Self-Supervised Representation Learning [82.79808902674282]
Contrastive learning has revolutionized unsupervised representation learning.
Current contrastive models are ineffective at localizing the foreground object.
We propose a data-driven approach for learning in variance to backgrounds.
arXiv Detail & Related papers (2020-04-14T16:29:42Z) - Rethinking Few-Shot Image Classification: a Good Embedding Is All You
Need? [72.00712736992618]
We show that a simple baseline: learning a supervised or self-supervised representation on the meta-training set, outperforms state-of-the-art few-shot learning methods.
An additional boost can be achieved through the use of self-distillation.
We believe that our findings motivate a rethinking of few-shot image classification benchmarks and the associated role of meta-learning algorithms.
arXiv Detail & Related papers (2020-03-25T17:58:42Z)
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.