Hybrid and dynamic policy gradient optimization for bipedal robot locomotion.

Changxin Huang Jiang Su Zhihong Zhang Dong Zhao Liang Lin

Published in: CoRR (2021)

Keyphrases

parametric optimization
mobile robot
policy gradient
autonomous robots
humanoid robot
robotic systems
optimization algorithm
dynamic environments
rough terrain
central pattern generator
neural network
optimization problems
monte carlo
path planning
closed loop