Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 1,424

The DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.

Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates

Open access
Gu, Shixiang, Holly, Ethan, Lillicrap, Timothy, Levine, Sergey · 2017 · 2017 IEEE International Conference on Robotics and Automation (ICRA)

Abstract

Reinforcement learning holds the promise of enabling autonomous robots to learn large repertoires of behavioral skills with minimal human intervention. However, robotic applications of reinforcement learning often compromise the autonomy of the learning process in favor of achieving training times that are practical for real physical systems. This typically involves introducing hand-engineered policy representations and human-supplied demonstrations. Deep reinforcement learning alleviates this limitation by training general-purpose neural network policies, but applications of direct deep reinforcement learning algorithms have so far been restricted to simulated settings and relatively simple tasks, due to their apparent high sample complexity. In this paper, we demonstrate that a recent deep reinforcement learning algorithm based on off-policy training of deep Q-functions can scale to complex 3D manipulation tasks and can learn deep neural network policies efficiently enough to train on real physical robots. We demonstrate that the training times can be further reduced by parallelizing the algorithm across multiple robots which pool their policy updates asynchronously. Our experimental evaluation shows that our method can learn a variety of 3D manipulation skills in simulation and a complex door opening skill on real robots without any prior demonstrations or manually designed representations.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/icra.2017.7989385

Cites

34 of 34 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

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

Research works printed but not linked: 8

  1. kuffner, 2010, Cloud-enabled humanoid robots, IEEE-RAS International Conference on Humanoid Robotics
  2. 10.1109/ICSMC.2004.1400771 · doi:10.1109/icsmc.2004.1400771
  3. tedrake, 0, Learning to walk in 20 minutes
  4. riedmiller, 2005, Neural fitted q in experiences with a data efficient neural reinforcement learning method, European Conference on Machine Learning, 317
  5. theodorou, 2010, Reinforcement learning of motor skills in high dimensions, ICRA
  6. 10.1145/2463372.2463509 · DOI · Paper page
  7. lioutikov, 2014, Sample-based information-theoretic stochastic optimal control, International Conference on Robotics and Automation
  8. deisenroth, 2013, A survey on policy search for robotics, Foundations and Trends in Robotics, 2, 1, 10.1561/2300000021 · DOI · Paper page

Cited by

See all 1,424

Metadata

Authors
Gu, S., Holly, E., Lillicrap, T., & Levine, S.
Venue
2017 IEEE International Conference on Robotics and Automation (ICRA)
Publisher
IEEE
Published
2017-05
Pages
3389-3396
ISSN
1050-4729 (ISSN-L)
OpenAlex
W2575705757
Cited by
1,424
References
34
FWCI
70.76
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.