Reinforcement learning for a biped robot based on a CPG-actor-critic method.

Yutaka Nakamura Takeshi Mori Masa-aki Sato Shin Ishii

Published in: Neural Networks (2007)

Keyphrases

reinforcement learning
dynamic programming
cost function
function approximation
model free
multi agent
artificial neural networks
fuzzy logic
computational intelligence
convergence rate
gradient method