Reinforcement learning for quasi-passive dynamic walking of an unstable biped robot
- 1 December 2006
- journal article
- Published by Elsevier in Robotics and Autonomous Systems
- Vol. 54 (12) , 982-988
Abstract
No abstract availableKeywords
This publication has 10 references indexed in Scilit:
- Stochastic policy gradient reinforcement learning on a simple 3D biped2005
- Efficient Bipedal Robots Based on Passive-Dynamic WalkersScience, 2005
- Natural Policy Gradient Reinforcement Learning for a CPG Control of a Biped Robot2004
- A Policy Representation Using Weighted Multiple Normal Distribution Real-time Reinforcement Learning Feasible for Varying Optimal Actions.Transactions of the Japanese Society for Artificial Intelligence, 2003
- Locomotor activity in spinal man: significance of afferent input from joint and load receptorsBrain, 2002
- Dimensional change in motor learningHuman Movement Science, 2001
- The pedunculopontine nucleus and Parkinson's diseaseBrain, 2000
- Determination of the step duration of gait initiation using a mechanical energy analysisJournal of Biomechanics, 1996
- Passive Dynamic WalkingThe International Journal of Robotics Research, 1990
- The Human Bicycle: An Ultimate Biological ConvenienceOrthopedic Clinics of North America, 1976