Imitation and Reinforcement Learning
The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
In this article, we present both novel learning algorithms and experiments using the dynamical system MPs. As such, we describe this MP representation in a way that it is straightforward to reproduce. We review an appropriate imitation learning method, i.e., locally weighted regression, and show how this method can be used both for initializing RL tasks as well as for modifying the start-up phase in a rhythmic task. We also show our current best-suited RL algorithm for this framework, i.e., PoWER. We present two complex motor tasks, i.e., ball-in-a-cup and ball paddling, learned on a real, physical Barrett WAM, using the methods presented in this article. Of particular interest is the ball-paddling application, as it requires a combination of both rhythmic and discrete dynamical systems MPs during the start-up phase to achieve a particular task.
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
Reinforcement 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
Self-citationSimple statistical gradient-following algorithms for connectionist reinforcement learning
Williams, R. J. (1992) · Machine Learning · doi:10.1023/a:1022672621406 · Cited by 817
Motor primitives in vertebrates and invertebrates
Flash, T., & Hochner, B. (2005) · Current Opinion in Neurobiology · doi:10.1016/j.conb.2005.10.011 · Cited by 508 · cited 1×
“, paddling a ball with a table-tennis racket, throwing darts, or hitting a tennis ball, it is highly likely that they rely on a small set of motor primitives (MPs) and use imitation as well as reinforcement learning (RL) [1].”
BackgroundDynamics systems vs. optimal control — a unifying view
Schaal, S., Mohajerian, P., & Ijspeert, A. (2007) · Progress in Brain Research · doi:10.1016/s0079-6123(06)65027-9 · Cited by 260
A Kendama Learning Robot Based on Bi-directional Theory
Miyamoto, H., Schaal, S., Gandolfo, F., Gomi, H., Koike, Y., Osu, R., Nakano, E., Wada, Y., & Kawato, M. (1996) · Neural Networks · doi:10.1016/s0893-6080(96)00043-3 · Cited by 171 · cited 1×
“[25], who used a 7 DoF anthropomorphic arm and recorded human”
MethodLearning to Control in Operational Space
Peters, J., & Schaal, S. (2008) · The International Journal of Robotics Research · doi:10.1177/0278364907087548 · Cited by 162 · cited 2×
“However, RL for MPs is a very specific type of learning problem, where it is hard to apply generic algorithms [4], [15] because of the high-dimensional states s 1⁄4 1⁄2z, x that defy discretization of the state space.”
BackgroundMethodSelf-citation
Cited by
Imitation Learning: A Survey of Learning Methods
Hussein, A., Gaber, M. M., Elyan, E., & Jayne, C. (2018) · ACM Computing Surveys · doi:10.1145/3054912 · Cited by 1,060
“Using damping in dynamic systems is a common approach when combining imitation learning and reinforcement learning [Kober and Peters 2010; Kober et al. 2013].”
BackgroundMethodInfluentialDynamic movement primitives in robotics: A tutorial survey
Saveriano, M., Abu-Dakka, F. J., Kramberger, A., & Peternel, L. (2023) · The International Journal of Robotics Research · doi:10.1177/02783649231201196 · Cited by 267
“IL arises as an effective approach to policy initialization and to speed up policy search by reducing the number of rollouts (Kober and Peters 2010).”
BackgroundAn artificial agent for robust image registration
Liao, R., Miao, S., De Tournemire, P., Grbic, S., Kamen, A., Mansi, T., & Comaniciu, D. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.11230 · Cited by 199
“Guided policy search (Levine and Koltun 2013) and imitation learning (Kober and Peters 2010) were proposed for more efficient RL via improved policy/data sampling, which however are not directly applicable to the end-to-end trainable DRL framework.”
BackgroundGTI: Learning to Generalize across Long-Horizon Tasks from Human Demonstrations
Mandlekar, A., Xu, D., Martín-Martín, R., Savarese, S., & Fei-Fei, L. (2020) · Robotics: Science and Systems XVI · doi:10.15607/rss.2020.xvi.061 · Cited by 90
Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations
Mandlekar, A., Xu, D., Martín-Martín, R., Savarese, S., & Fei-Fei, L. (2020) · arXiv · doi:10.48550/arxiv.2003.06085 · Cited by 17
“Imitation learning has been applied to multiple domains such as playing table tennis [22], Go [37] and video games [33], and driving autonomously [4, 31] In robotics, the idea of robots learning from human demonstrations have been extensively explored [36, 17, 23, 11, 14, 3, 5].”
Background
Metadata
- Authors
- Kober, J., & Peters, J.
- Venue
- IEEE Robotics & Automation Magazine
- Published
- 2010-06
- Volume
- 17
- Issue
- 2
- Pages
- 55-62
- ISSN
- 1070-9932 (ISSN-L)
- OpenAlex
- W2071841410
- Cited by
- 133
- References
- 6
- FWCI
- 9.52
- Type
- journal article
- 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
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.