Learning CPG-based biped locomotion with a policy gradient method
- 1 November 2006
- journal article
- Published by Elsevier in Robotics and Autonomous Systems
- Vol. 54 (11) , 911-920
- https://doi.org/10.1016/j.robot.2006.05.012
Abstract
No abstract availableKeywords
This publication has 18 references indexed in Scilit:
- An empirical exploration of a neural oscillator for biped locomotion controlPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Adaptive Dynamic Walking of a Quadruped Robot on Irregular Terrain Based on Biological ConceptsThe International Journal of Robotics Research, 2003
- Reinforcement Learning for Biped LocomotionPublished by Springer Nature ,2002
- Infinite-Horizon Policy-Gradient EstimationJournal of Artificial Intelligence Research, 2001
- Reinforcement Learning in Continuous Time and SpaceNeural Computation, 2000
- Computer Simulation of the Ontogeny of Bipedal Walking.Anthropological Science, 1998
- Learning Without State-Estimation in Partially Observable Markovian Decision ProcessesPublished by Elsevier ,1994
- Simple statistical gradient-following algorithms for connectionist reinforcement learningMachine Learning, 1992
- Self-organized control of bipedal locomotion by neural oscillators in unpredictable environmentBiological Cybernetics, 1991
- Sustained oscillations generated by mutually inhibiting neurons with adaptationBiological Cybernetics, 1985