One-shot learning of manipulation skills with online dynamics adaptation and neural network priors
Open accessThe DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
One of the key challenges in applying reinforcement learning to complex robotic control tasks is the need to gather large amounts of experience in order to find an effective policy for the task at hand. Model-based reinforcement learning can achieve good sample efficiency, but requires the ability to learn a model of the dynamics that is good enough to learn an effective policy. In this work, we develop a model-based reinforcement learning algorithm that combines prior knowledge from previous tasks with online adaptation of the dynamics model. These two ingredients enable highly sample-efficient learning even in regimes where estimating the true dynamics is very difficult, since the online model adaptation allows the method to locally compensate for unmodeled variation in the dynamics. We encode the prior experience into a neural network dynamics model, adapt it online by progressively refitting a local linear model of the dynamics, and use model predictive control to plan under these dynamics. Our experimental results show that this approach can be used to solve a variety of complex robotic manipulation tasks in just a single attempt, using prior data from other manipulation behaviors.
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
MuJoCo: A physics engine for model-based control
Todorov, E., Erez, T., & Tassa, Y. (2012) · 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2012.6386109 · Cited by 4,767
Reinforcement learning in robotics: A survey
Kober, J., Bagnell, J. A., & Peters, J. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913495721 · Cited by 3,160 · cited 2×
“produce accurate dynamics predictions [2].”
MethodReinforcement learning of motor skills with policy gradients
Peters, J., & Schaal, S. (2008) · Neural Networks · doi:10.1016/j.neunet.2008.02.003 · Cited by 831
Cited by
Electronic skins and machine learning for intelligent soft robots
Shih, B., Shah, D., Li, J., Thuruthel, T. G., Park, Y.-L., Iida, F., Bao, Z., Kramer-Bottiglio, R., & Tolley, M. T. (2020) · Science Robotics · doi:10.1126/scirobotics.aaz9239 · Cited by 715
“A general trend observed in such works is the success of model-based RL ( 67 ) or learning by demonstration ( 68 ), approaches that leverage techniques from control theory or human knowledge, respectively.”
BackgroundModel-Ensemble Trust-Region Policy Optimization
Kurutach, T., Clavera, I., Duan, Y., Tamar, A., & Abbeel, P. (2018) · arXiv · doi:10.48550/arxiv.1802.10592 · Cited by 537
Self-citationDeep reinforcement learning in a handful of trials using probabilistic dynamics models
Chua, K., Calandra, R., McAllister, R., & Levine, S. (2018) · arXiv · doi:10.48550/arxiv.1805.12114 · Cited by 525
Self-citationModel-based Reinforcement Learning: A Survey
M. Moerland, T., Broekens, J., Plaat, A., & M. Jonker, C. (2023) · Foundations and Trends in Machine Learning · doi:10.1561/2200000086 · Cited by 524
Learning to Adapt in Dynamic, Real-World Environments through Meta-Reinforcement Learning
Nagabandi, A., Clavera, I., Liu, S., Fearing, R. S., Abbeel, P., Levine, S., & Finn, C. (2018) · arXiv · doi:10.48550/arxiv.1803.11347 · Cited by 370
“…∆st caused by taking action at from state st. Predicting state difference, rather than next state, allows the neural network to learn more than just the identity function, especially when the change in state is small (Deisenroth & Rasmussen, 2011; Fu et al., 2016; Nagabandi et al., 2017a).”
BackgroundSelf-citation
Metadata
- Authors
- Fu, J., Levine, S., & Abbeel, P.
- Venue
- 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
- Publisher
- IEEE
- Published
- 2016-10
- Pages
- 4019-4026
- OpenAlex
- W2963280855
- Cited by
- 121
- References
- 3
- FWCI
- 9.44
- 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
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.