Collective robot reinforcement learning with distributed asynchronous guided policy search
Open accessThe DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
Policy search methods and, more broadly, reinforcement learning can enable robots to learn highly complex and general skills that may allow them to function amid the complexity and diversity of the real world. However, training a policy that generalizes well across a wide range of real-world conditions requires far greater quantity and diversity of experience than is practical to collect with a single robot. Fortunately, it is possible for multiple robots to share their experience with one another, and thereby, learn a policy collectively. In this work, we explore distributed and asynchronous policy learning as a means to achieve generalization and improved training times on challenging, real-world manipulation tasks. We propose a distributed and asynchronous version of guided policy search and use it to demonstrate collective policy learning on a vision-based door opening task using four robots. We describe how both policy learning and data collection can be conducted in parallel across multiple robots, and present a detailed empirical evaluation of our system. Our results indicate that distributed learning significantly improves training time, and that parallelizing policy learning and data collection substantially improves utilization. We also demonstrate that we can achieve substantial generalization on a challenging real-world door opening 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
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Continuous control with deep reinforcement learning
Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., & Wierstra, D. (2015) · arXiv · doi:10.48550/arxiv.1509.02971 · Cited by 10,782
Asynchronous Methods for Deep Reinforcement Learning
Mnih, V., Badia, A. P., Mirza, M., Graves, A., Lillicrap, T. P., Harley, T., Silver, D., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1602.01783 · Cited by 7,132 · cited 2×
“Indeed, prior asynchronous reinforcement learning methods report an enormous decrease in sample efficiency [16], with effective sample sizes for even simple continuous control policies measured in millions of time steps, which would be days of experience if it were collected in real time.”
BackgroundLevine, S., Pastor, P., Krizhevsky, A., Ibarz, J., & Quillen, D. (2018) · The International Journal of Robotics Research · doi:10.1177/0278364917710318 · Cited by 1,971
Self-citationGoing Further with Point Pair Features
Hinterstoisser, S., Lepetit, V., Rajkumar, N., & Konolige, K. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46487-9_51 · Cited by 201 · cited 1×
“The labels are obtained automatically from a geometry-based pose estimator [28] and from the robot’s forward kinematics.”
Method
Cited by
Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates
Gu, S., Holly, E., Lillicrap, T., & Levine, S. (2017) · 2017 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2017.7989385 · Cited by 1,424
Self-citationQT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
Kalashnikov, D., Irpan, A., Pastor, P., Ibarz, J., Herzog, A., Jang, E., Quillen, D., Holly, E., Kalakrishnan, M., Vanhoucke, V., et al. (2018) · arXiv · doi:10.48550/arxiv.1806.10293 · Cited by 697
Self-citationChallenges of real-world reinforcement learning: definitions, benchmarks and analysis
Dulac-Arnold, G., Levine, N., Mankowitz, D. J., Li, J., Paduraru, C., Gowal, S., & Hester, T. (2021) · Machine Learning · doi:10.1007/s10994-021-05961-4 · Cited by 645
Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience
Chebotar, Y., Handa, A., Makoviychuk, V., Macklin, M., Issac, J., Ratliff, N., & Fox, D. (2019) · 2019 International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2019.8793789 · Cited by 457
Self-citationFaust, A., Oslund, K., Ramirez, O., Francis, A., Tapia, L., Fiser, M., & Davidson, J. (2018) · 2018 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2018.8461096 · Cited by 327
Metadata
- Authors
- Yahya, A., Li, A., Kalakrishnan, M., Chebotar, Y., & Levine, S.
- Venue
- 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
- Publisher
- IEEE
- Published
- 2017-09
- Pages
- 79-86
- OpenAlex
- W2529658650
- Cited by
- 130
- References
- 5
- FWCI
- 8.51
- 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.