Policy gradient reinforcement learning for fast quadrupedal locomotion
Top Cited Papers
- 1 January 2004
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3 (10504729) , 2619-2624 Vol.3
- https://doi.org/10.1109/robot.2004.1307456
Abstract
This paper presents a machine learning approach to optimizing a quadrupedal trot gait for forward speed. Given a parameterized walk designed for a specific robot, we propose using a form of policy gradient reinforcement learning to automatically search the set of possible parameters with the goal of finding the fastest possible walk. We implement and test our approach on a commercially available quadrupedal robot platform, namely the Sony Aibo robot. After about three hours of learning, all on the physical robots and with no human intervention other than to change the batteries, the robots achieved a gait faster than any previously known gait known for the Aibo, significantly outperforming a variety of existing hand-coded and learned solutions.Keywords
This publication has 3 references indexed in Scilit:
- Autonomous helicopter control using reinforcement learning policy search methodsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Evolving robust gaits with AIBOPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Infinite-Horizon Policy-Gradient EstimationJournal of Artificial Intelligence Research, 2001