Hybrid control for learning motor skills

DOI10.1007/978-3-030-66723-8_27zbMATH Open1471.93184arXiv2006.03636OpenAlexW3132508462MaRDI QIDQ3381995FDOQ3381995

Authors: Ian Abraham, Alexander Broad, Allison Pinosky, Brenna D. Argall, T. D. Murphey 

Publication date: 20 September 2021

Published in: Algorithmic Foundations of Robotics XIV (Search for Journal in Brave)

Abstract: We develop a hybrid control approach for robot learning based on combining learned predictive models with experience-based state-action policy mappings to improve the learning capabilities of robotic systems. Predictive models provide an understanding of the task and the physics (which improves sample-efficiency), while experience-based policy mappings are treated as "muscle memory" that encode favorable actions as experiences that override planned actions. Hybrid control tools are used to create an algorithmic approach for combining learned predictive models with experience-based learning. Hybrid learning is presented as a method for efficiently learning motor skills by systematically combining and improving the performance of predictive models and experience-based policies. A deterministic variation of hybrid learning is derived and extended into a stochastic implementation that relaxes some of the key assumptions in the original derivation. Each variation is tested on experience-based learning methods (where the robot interacts with the environment to gain experience) as well as imitation learning methods (where experience is provided through demonstrations and tested in the environment). The results show that our method is capable of improving the performance and sample-efficiency of learning motor skills in a variety of experimental domains.

Full work available at URL: https://arxiv.org/abs/2006.03636

Recommendations

• Towards motor skill learning for robotics
• Model-based contextual policy search for data-efficient generalization of robot skills
• Robot control policy transfer based on progressive neural network
• scientific article; zbMATH DE number 4172860
• Robot motor skill acquisition with alternate learning in two spaces

zbMATH Keywords

learning theoryoptimal controlhybrid control theory

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Automated systems (robots, etc.) in control theory (93C85) Optimal stochastic control (93E20)

Cites Work

• Gradient descent approach to optimal mode scheduling in hybrid dynamical systems

Cited In (2)

• A Developmental Approach Aids Motor Learning
• Methods for learning control policies from variable-constraint demonstrations

Uses Software

• PILCO
• Pybullet

This page was built for publication: Hybrid control for learning motor skills

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3381995)