Learning CPG-based Biped Locomotion with a Policy Gradient Method: Application to a Humanoid Robot.

Gen Endo Jun Morimoto Takamitsu Matsubara Jun Nakanishi Gordon Cheng Learning CPG-based Biped Locomotion with a Policy Gradient Method: Application to a Humanoid Robot. 213-228 2008 27 I. J. Robotic Res. 2 http://dx.doi.org/10.1177/0278364907084980 db/journals/ijrr/ijrr27.html#EndoMMNC08