Path integral guided policy search
The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
We present a policy search method for learning complex feedback control policies that map from high-dimensional sensory inputs to motor torques, for manipulation tasks with discontinuous contact dynamics. We build on a prior technique called guided policy search (GPS), which iteratively optimizes a set of local policies for specific instances of a task, and uses these to train a complex, high-dimensional global policy that generalizes across task instances. We extend GPS in the following ways: (1) we propose the use of a model-free local optimizer based on path integral stochastic optimal control (PI2), which enables us to learn local policies for tasks with highly discontinuous contact dynamics; and (2) we enable GPS to train on a new set of task instances in every iteration by using on-policy sampling: this increases the diversity of the instances that the policy is trained on, and is crucial for achieving good generalization. We show that these contributions enable us to learn deep neural network policies that can directly perform torque control from visual input. We validate the method on a challenging door opening task and a pick-and-place task, and we demonstrate that our approach substantially outperforms the prior LQR-based local policy optimizer on these tasks. Furthermore, we show that on-policy sampling significantly increases the generalization ability of these policies.
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
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
Fukushima, K. (1980) · Biological Cybernetics · doi:10.1007/bf00344251 · Cited by 5,759 · cited 1×
“The features are learned automatically on a pose detection proxy task, using an improved version of the spatial feature points architecture [6] based on convolutional neural networks (CNNs) [29, 30].”
MethodLearning and generalization of motor skills by learning from demonstration
Pastor, P., Hoffmann, H., Asfour, T., & Schaal, S. (2009) · 2009 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2009.5152385 · Cited by 702
Going 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 2×
“We use object detection with PPF [34] to determine the final pose to evaluate the cost.”
MethodLearning force control policies for compliant manipulation
Kalakrishnan, M., Righetti, L., Pastor, P., & Schaal, S. (2011) · 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2011.6095096 · Cited by 161 · cited 1×
“In [23], PI(2) is used to learn force/torque profiles for door opening and picking tasks to improve imperfect kinesthetic demonstrations.”
Self-citation
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
“Recent works used learning-based methods for slip onset prediction with adjustment and grasp failure detection with adjustment because of the ability of these methods to handle complex multimodal sensory information (84) and their generalizability (85).”
MethodHow to train your robot with deep reinforcement learning: Lessons we have learned
Ibarz, J., Tan, J., Finn, C., Kalakrishnan, M., Pastor, P., & Levine, S. (2021) · The International Journal of Robotics Research · doi:10.1177/0278364920987859 · Cited by 570
Self-citationVerl, A., Valente, A., Melkote, S., Brecher, C., Ozturk, E., & Tunc, L. T. (2019) · CIRP Annals · doi:10.1016/j.cirp.2019.05.009 · Cited by 392
Lee, M. A., Zhu, Y., Srinivasan, K., Shah, P., Savarese, S., Fei-Fei, L., Garg, A., & Bohg, J. (2019) · 2019 International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2019.8793485 · Cited by 349
“While learning-based methods do not require manual task specification, the majority of learned manipulation policies close the control loop around a single modality, often vision [15, 21, 34, 58].”
BackgroundMotion Planning Networks: Bridging the Gap Between Learning-Based and Classical Motion Planners
Qureshi, A. H., Miao, Y., Simeonov, A., & Yip, M. C. (2021) · IEEE Transactions on Robotics · doi:10.1109/tro.2020.3006716 · Cited by 287
Metadata
- Authors
- Chebotar, Y., Kalakrishnan, M., Yahya, A., Li, A., Schaal, S., & Levine, S.
- Venue
- 2017 IEEE International Conference on Robotics and Automation (ICRA)
- Publisher
- IEEE
- Published
- 2017-05
- Pages
- 3381-3388
- ISSN
- 1050-4729 (ISSN-L)
- OpenAlex
- W2529601334
- Cited by
- 117
- References
- 5
- FWCI
- 8.13
- Type
- conference paper
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Path integral guided policy search. https://app.cochat.ai/papers/10.1109/icra.2017.7989384
- The paper
- Chebotar, Y., Kalakrishnan, M., Yahya, A., Li, A., Schaal, S., & Levine, S. (2017). Path integral guided policy search. 2017 IEEE International Conference on Robotics and Automation (ICRA). https://doi.org/10.1109/icra.2017.7989384
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.