Curious Representation Learning for Embodied Intelligence
The DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
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/.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Proximal Policy Optimization Algorithms
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017) · arXiv · doi:10.48550/arxiv.1707.06347 · Cited by 10,625
Unsupervised Feature Learning via Non-parametric Instance Discrimination
Wu, Z., Xiong, Y., Yu, S. X., & Lin, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00393 · Cited by 3,664
Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles
Noroozi, M., & Favaro, P. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46466-4_5 · Cited by 2,775
Tian, Y., Krishnan, D., & Isola, P. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58621-8_45 · Cited by 1,997
Self-citationMatterport3D: Learning from RGB-D Data in Indoor Environments
Chang, A., Dai, A., Funkhouser, T., Halber, M., Niebner, M., Savva, M., Song, S., Zeng, A., & Zhang, Y. (2017) · 2017 International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2017.00081 · Cited by 1,858
Curiosity-Driven Exploration by Self-Supervised Prediction
Pathak, D., Agrawal, P., Efros, A. A., & Darrell, T. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.70 · Cited by 1,815 · cited 4×
“Curiosity has also been studied extensively in the past years [5, 8, 14, 24, 29, 34, 35], as both an incentive for exploration as well as a means of achieving emergent complex behavior.”
BackgroundResultInfluentialHabitat: A Platform for Embodied AI Research
Savva, M., Kadian, A., Maksymets, O., Zhao, Y., Wijmans, E., Jain, B., Straub, J., Liu, J., Koltun, V., Malik, J., et al. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00943 · Cited by 1,237 · cited 6×
“In contrast to prior work, which focuses on synthetic game environments, we study representation learning in photorealistic 3D environments [16, 33, 48].”
BackgroundMethodResultInfluential
Research works printed but not linked: 22
- srinivas, 2020, Curl Contrastive unsupervised representations for reinforcement learning
- ross, 2010, No-regret reductions for imitation learning and structured prediction, CoRR
- 10.1007/978-3-319-46475-6_1 · DOI
- schwarzer, 2020, Data-efficient reinforcement learning with self-predictive representations
- schmidhuber, 1991, A possibility for implementing curiosity and boredom in model-building neural controllers, Proc of the International Conference on Simulation of Adaptive Behavior From Animals to Animats, 222, 10.7551/mitpress/3115.003.0030 · DOI · Paper page
- schmidhuber, 1990, Making the world differentiable: On using fully recurrent self-supervised neural networks for dynamic reinforcement learning and planning in non-stationary environments, Institut für Informatik Technische Universität München Technical Report FKI-126, 90
- anand, 2020, Unsupervised state representation learning in atari
- agrawal, 2016, Learning to poke by poking: Experiential learning of intuitive physics, NIPS
- houthooft, 2016, Vime: Variational information maximizing exploration, Advances in neural information processing systems, 1109
- jaderberg, 2016, Reinforcement learning with unsupervised auxiliary tasks
- zhang, 2016, Colorful image colorization, ECCV
- zhu, 2018, Toward multimodal image-to-image translation
- 10.1109/CVPR.2018.00586 · DOI · Paper page
- bachman, 2019, Learning representations by maximizing mutual information across views, Advances in neural information processing systems, 15509
- anderson, 2018, On evaluation of embodied navigation agents
- 10.1109/TPAMI.2013.50 · DOI · Paper page
- bellemare, 2016, Unifying count-based exploration and intrinsic motivation, Advances in neural information processing systems, 1471
- ye, 2020, Auxiliary tasks speed up learning pointgoal navigation, CoRL
- 10.1109/CVPR.2018.00945 · DOI · Paper page
- tang, 2017, #exploration: A study of count-based exploration for deep reinforcement learning, Advances in neural information processing systems, 30
- sutskever, 2014, Sequence to sequence learning with neural networks, NIPS
- tian, 2020, Rethinking few-shot image classification: a good embedding is all you need?, 10.1007/978-3-030-58568-6_16 · DOI · Paper page
Cited by
Habitat 2.0: Training home assistants to rearrange their habitat
Szot, A., Clegg, A., Undersander, E., Wijmans, E., Zhao, Y., Turner, J., Maestre, N., Mukadam, M., Chaplot, D., Maksymets, O., et al. (2021) · arXiv · doi:10.48550/arxiv.2106.14405 · Cited by 143
“[14] Yilun Du, Chuang Gan, and Phillip Isola.”
BackgroundZero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation
Al-Halah, Z., Ramakrishnan, S. K., & Grauman, K. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01652 · Cited by 58
“3) CRL [22] pretrains fO (ResNet50) using a combination of curiosity-based exploration and self-supervised learning.”
MethodInfluentialAn Information-Theoretic Perspective on Intrinsic Motivation in Reinforcement Learning: A Survey
Aubret, A., Matignon, L., & Hassas, S. (2023) · Entropy · doi:10.3390/e25020327 · Cited by 52
Learning Navigational Visual Representations with Semantic Map Supervision
Hong, Y., Zhou, Y., Zhang, R., Dernoncourt, F., Bui, T., Gould, S., & Tan, H. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00284 · Cited by 42
“In terms of self-supervised visual representation learning for indoor navigation, recent works that are the most relevant to ours include OVRL [96] which applies knowledge distillation based on DINO [6], EPC which predicts masked observations from a trajectory [75], and CRL which jointly learns a visual encoder with a…”
MethodPrioritized Semantic Learning for Zero-Shot Instance Navigation
Sun, X., Liu, L., Zhi, H., Qiu, R., & Liang, J. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-73254-6_10 · Cited by 12
Metadata
- Authors
- Du, Y., Gan, C., & Isola, P.
- Venue
- 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2021-10
- Pages
- 10388-10397
- OpenAlex
- W3165538103
- Cited by
- 32
- References
- 17
- FWCI
- 2.22
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Curious Representation Learning for Embodied Intelligence. https://app.cochat.ai/papers/10.1109/iccv48922.2021.01024
- The paper
- Du, Y., Gan, C., & Isola, P. (2021). Curious Representation Learning for Embodied Intelligence. 2021 IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/iccv48922.2021.01024
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.