An extended policy gradient algorithm for robot task learning.

Andrea Cherubini Francesca Giannone Luca Iocchi Pier Francesco Palamara

Published in: IROS (2007)

Keyphrases

learning algorithm
policy gradient
actor critic
computational complexity
path planning
machine learning
reinforcement learning
cost function
dynamic programming
support vector
multi agent systems
monte carlo
learning tasks
learning problems
function approximation