Policy gradient learning for a humanoid soccer robot.

Andrea Cherubini Francesca Giannone Luca Iocchi M. Lombardo Giuseppe Oriolo

Published in: Robotics Auton. Syst. (2009)

Keyphrases

policy gradient
learning process
learning algorithm
supervised learning
path planning
reinforcement learning
multi agent
learning tasks
humanoid robot
machine learning
state space
learning capabilities