Curious Representation Learning for Embodied Intelligence
By Yilun Du, Chuang Gan, Phillip Isola. 2021
52 citations recorded by the source corpus.
Self-supervised representation learning has achieved remarkable success in recent years. By subverting the need for supervised labels, such approaches are able to utilize the numerous unlabeled images that exist on the Internet and in photographic datasets. Yet to build truly intelligent agents, we must construct representation learning algorithms that can learn not only from datasets but also learn from environments. An agent in a natural environment will not typically be fed curated data. Instead, it must explore its environment to acquire the data it will learn from. We propose a framework, curious representation learning (CRL), which jointly learns a reinforcement learning policy and a visual representation model. The policy is trained to maximize the error of the representation learner, and in doing so is incentivized to explore its environment. At the same time, the learned representation becomes stronger and stronger as the policy feeds it ever harder data to learn from. Our learned representations enable promising transfer to downstream navigation tasks, performing better than or comparably to ImageNet pretraining without using any supervision at all. In addition, despite being trained in simulation, our learned representations can obtain interpretable results on real images. Code is available at https://yilundu.github.io/crl/.
Subfields: Representation & Self-Supervised Learning, Robotics & Control
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Representation & Self-Supervised Learning
- Jitendra Malik
- Dhruv Batra
- Sergey Levine
- Ruslan Salakhutdinov
- Zsolt Kira
- Benjamin Eysenbach
- Vladlen Koltun
- F. Meier
In Robotics & Control
- Dhruv Batra
- Sergey Levine
- Vladlen Koltun
- Jitendra Malik
- Ruslan Salakhutdinov
- Manolis Savva
- Benjamin Eysenbach
- Devendra Singh Chaplot
Citations in the corpus
- Habitat 2.0: Training Home Assistants to Rearrange their Habitat (2021, background): “[14] Yilun Du, Chuang Gan, and Phillip Isola.”
- Contrastive Learning as Goal-Conditioned Reinforcement Learning (2022, methodology): “The problems of automatically sampling goals and exploration [23, 34, 85, 98, 144] are orthogonal to this work.”
- Semantic Exploration from Language Abstractions and Pretrained Representations (2022, background): “Self-supervised representation learning techniques distill knowledge from external datasets to produce downstream features that are helpful in virtual environments [15, 53].”