Adversarial Skill Networks: Unsupervised Robot Skill Learning from Video
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
Key challenges for the deployment of reinforcement learning (RL) agents in the real world are the discovery, representation and reuse of skills in the absence of a reward function. To this end, we propose a novel approach to learn a task-agnostic skill embedding space from unlabeled multi-view videos. Our method learns a general skill embedding independently from the task context by using an adversarial loss. We combine a metric learning loss, which utilizes temporal video coherence to learn a state representation, with an entropy-regularized adversarial skill-transfer loss. The metric learning loss learns a disentangled representation by attracting simultaneous viewpoints of the same observations and repelling visually similar frames from temporal neighbors. The adversarial skill-transfer loss enhances re-usability of learned skill embeddings over multiple task domains. We show that the learned embedding enables training of continuous control policies to solve novel tasks that require the interpolation of previously seen skills. Our extensive evaluation with both simulation and real world data demonstrates the effectiveness of our method in learning transferable skills from unlabeled interaction videos and composing them for new tasks. Code, pretrained models and dataset are available at http://robotskills.cs.uni-freiburg.de.
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
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
A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
Silver, D., Hubert, T., Schrittwieser, J., Antonoglou, I., Lai, M., Guez, A., Lanctot, M., Sifre, L., Kumaran, D., Graepel, T., et al. (2018) · Science · doi:10.1126/science.aar6404 · Cited by 3,562
Rainbow: Combining Improvements in Deep Reinforcement Learning
Hessel, M., Modayil, J., Van Hasselt, H., Schaul, T., Ostrovski, G., Dabney, W., Horgan, D., Piot, B., Azar, M., & Silver, D. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11796 · Cited by 1,846
DeepMimic: example-guided deep reinforcement learning of physics-based character skills
Peng, X. B., Abbeel, P., Levine, S., & van de Panne, M. (2018) · ACM Transactions on Graphics · doi:10.1145/3197517.3201311 · Cited by 1,784
Deep visual foresight for planning robot motion
Finn, C., & Levine, S. (2017) · 2017 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2017.7989324 · Cited by 599
Distributed Distributional Deterministic Policy Gradients
Barth-Maron, G., Hoffman, M. W., Budden, D., Dabney, W., Horgan, D., TB, D., Muldal, A., Heess, N., & Lillicrap, T. (2018) · arXiv · doi:10.48550/arxiv.1804.08617 · Cited by 567
Sim-to-Real Robot Learning from Pixels with Progressive Nets
Rusu, A. A., Vecerik, M., Rothörl, T., Heess, N., Pascanu, R., & Hadsell, R. (2016) · arXiv · doi:10.48550/arxiv.1610.04286 · Cited by 385 · cited 1×
“the installation of specific sensors to measure as to whether the task has been executed successfully [4], [5].”
BackgroundMONet: Unsupervised Scene Decomposition and Representation
Burgess, C. P., Matthey, L., Watters, N., Kabra, R., Higgins, I., Botvinick, M., & Lerchner, A. (2019) · arXiv · doi:10.48550/arxiv.1901.11390 · Cited by 270
Learning Dexterous In-Hand Manipulation
OpenAI, Andrychowicz, M., Baker, B., Chociej, M., Jozefowicz, R., McGrew, B., Pachocki, J., Petron, A., Plappert, M., Powell, G., et al. (2018) · arXiv · doi:10.48550/arxiv.1808.00177 · Cited by 248
Reward learning from human preferences and demonstrations in Atari
Ibarz, B., Leike, J., Pohlen, T., Irving, G., Legg, S., & Amodei, D. (2018) · arXiv · doi:10.48550/arxiv.1811.06521 · Cited by 117
Cited by
Mees, O., Hermann, L., Rosete-Beas, E., & Burgard, W. B. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3180108 · Cited by 189
Self-citationWhat matters in language conditioned robotic imitation learning over unstructured data
Mees, O., Hermann, L., & Burgard, W. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3196123 · Cited by 77
Self-citationXIRL: Cross-embodiment inverse reinforcement learning
Zakka, K., Zeng, A., Florence, P., Tompson, J., Bohg, J., & Dwibedi, D. (2021) · arXiv · doi:10.48550/arxiv.2106.03911 · Cited by 38
Affordance Learning from Play for Sample-Efficient Policy Learning
Borja-Diaz, J., Mees, O., Kalweit, G., Hermann, L., Boedecker, J., & Burgard, W. (2022) · 2022 International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra46639.2022.9811889 · Cited by 32
Self-citation
Metadata
- Authors
- Mees, O., Merklinger, M., Kalweit, G., & Burgard, W.
- Venue
- 2020 IEEE International Conference on Robotics and Automation (ICRA)
- Publisher
- IEEE
- Published
- 2020-05
- Pages
- 4188-4194
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W2980558778
- Cited by
- 26
- References
- 10
- FWCI
- 2.02
- Type
- conference paper
- Language
- en
- Open access
- green
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: Adversarial Skill Networks: Unsupervised Robot Skill Learning from Video. https://app.cochat.ai/papers/10.1109/icra40945.2020.9196582
- The paper
- Mees, O., Merklinger, M., Kalweit, G., & Burgard, W. (2020). Adversarial Skill Networks: Unsupervised Robot Skill Learning from Video. 2020 IEEE International Conference on Robotics and Automation (ICRA). https://doi.org/10.1109/icra40945.2020.9196582
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.