Reinforcement learning for a biped robot based on a CPG-actor-critic method
Authors:
- Yutaka NakamuraYNYutaka Nakamura
- Takeshi MoriTMTakeshi Mori
- Masa-Aki SatoMSMasa-Aki Sato
- Shin IshiiSIShin Ishii
- 1 August 2007
- journal article
- Published by Elsevier in Neural Networks
- Vol. 20 (6) , 723-735
Abstract
No abstract availableKeywords
This publication has 37 references indexed in Scilit:
- On-line learning of a feedback controller for quasi-passive-dynamic walking by a stochastic policy gradient method2005
- A Novel Gait Generation for Biped Walking Robots Based on Mechanical Energy ConstraintIEEE Transactions on Robotics and Automation, 2004
- Humanoid robot learning and game playing using PC-based vision2003
- Adaptive Dynamic Walking of a Quadruped Robot on Irregular Terrain Based on Biological ConceptsThe International Journal of Robotics Research, 2003
- The development of Honda humanoid robot2002
- Walknet—a biologically inspired network to control six-legged walkingNeural Networks, 1998
- Natural Gradient Works Efficiently in LearningNeural Computation, 1998
- Linear Least-Squares algorithms for temporal difference learningMachine Learning, 1996
- A combined neuronal and mechanical model of fish swimmingBiological Cybernetics, 1993
- Neuronal Network Generating Locomotor Behavior in Lamprey: Circuitry, Transmitters, Membrane Properties, and SimulationAnnual Review of Neuroscience, 1991