Bootstrapping of parameterized skills through hybrid optimization in task and policy spaces

Queißer J, Steil JJ (2018)
Frontiers in Robotics and AI 5: 49.

Download
OA 3.86 MB
Journal Article | Original Article | Published | English
Abstract / Notes
Modern robotic applications create high demands on adaptation of actions with respect to variance in a given task. Reinforcement learning is able to optimize for these changing conditions, but relearning from scratch is hardly feasible due to the high number of required rollouts. We propose a parameterized skill that generalizes to new actions for changing task parameters, which is encoded as a meta-learner that provides parameters for task-specific dynamic motion primitives. Our work shows that utilizing parameterized skills for initialization of the optimization process leads to a more effective incremental task learning. In addition, we introduce a hybrid optimization method that combines a fast coarse optimization on a manifold of policy parameters with a fine grained parameter search in the unrestricted space of actions. The proposed algorithm reduces the number of required rollouts for adaptation to new task conditions. Application in illustrative toy scenarios, for a 10-DOF planar arm, and a humanoid robot point reaching task validate the approach.
Publishing Year
eISSN
Financial disclosure
Article Processing Charge funded by the Deutsche Forschungsgemeinschaft and the Open Access Publication Fund of Bielefeld University.
PUB-ID

Cite this

Queißer J, Steil JJ. Bootstrapping of parameterized skills through hybrid optimization in task and policy spaces. Frontiers in Robotics and AI. 2018;5:49.
Queißer, J., & Steil, J. J. (2018). Bootstrapping of parameterized skills through hybrid optimization in task and policy spaces. Frontiers in Robotics and AI, 5, 49. doi:10.3389/frobt.2018.00049
Queißer, J., and Steil, J. J. (2018). Bootstrapping of parameterized skills through hybrid optimization in task and policy spaces. Frontiers in Robotics and AI 5, 49.
Queißer, J., & Steil, J.J., 2018. Bootstrapping of parameterized skills through hybrid optimization in task and policy spaces. Frontiers in Robotics and AI, 5, p 49.
J. Queißer and J.J. Steil, “Bootstrapping of parameterized skills through hybrid optimization in task and policy spaces”, Frontiers in Robotics and AI, vol. 5, 2018, pp. 49.
Queißer, J., Steil, J.J.: Bootstrapping of parameterized skills through hybrid optimization in task and policy spaces. Frontiers in Robotics and AI. 5, 49 (2018).
Queißer, Jeffrey, and Steil, Jochen J. “Bootstrapping of parameterized skills through hybrid optimization in task and policy spaces”. Frontiers in Robotics and AI 5 (2018): 49.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Main File(s)
Access Level
OA Open Access
Last Uploaded
2018-06-19T06:39:37Z

This data publication is cited in the following publications:
This publication cites the following data publications:

Export

0 Marked Publications

Open Data PUB

Web of Science

View record in Web of Science®

Search this title in

Google Scholar