Reinforcement learning applied to legged-robots opens up the possibility to design robots capable not simply of walking, but of adapting and learning how to walk autonomously without any human interaction. This new generation of robots can one day navigate disaster areas and explore unchartered terrain. In this paper we evaluate the need for a reinforcement learning algorithm to optimize the gait of OctoRoACH, a hand-sized eight-legged robot. We then perform an evaluation of a likelihood-ratio gradient policy and compare it against our hand-tuned results. Finally, we suggest a different approach to reduce the policy search space that can make the problem more manageable.
Title
Reinforcement Learning Methods to Enable Automatic Tuning of Legged Robots
Published
2012-05-30
Full Collection Name
Electrical Engineering & Computer Sciences Technical Reports
Other Identifiers
EECS-2012-129
Type
Text
Extent
16 p
Archive
The Engineering Library
Usage Statement
Researchers may make free and open use of the UC Berkeley Library’s digitized public domain materials. However, some materials in our online collections may be protected by U.S. copyright law (Title 17, U.S.C.). Use or reproduction of materials protected by copyright beyond that allowed by fair use (Title 17, U.S.C. § 107) requires permission from the copyright owners. The use or reproduction of some materials may also be restricted by terms of University of California gift or purchase agreements, privacy and publicity rights, or trademark law. Responsibility for determining rights status and permissibility of any use or reproduction rests exclusively with the researcher. To learn more or make inquiries, please see our permissions policies (https://www.lib.berkeley.edu/about/permissions-policies).
