Alternating Optimisation and Quadrature for Robust Reinforcement Learning.

Supratik Paul Kamil Ciosek Michael A. Osborne Shimon Whiteson

Published in: CoRR (2016)

Keyphrases

reinforcement learning
function approximation
data mining
computationally efficient
fourier transform
real time
learning algorithm
computer vision
policy search
parameter tuning
optimal control
evaluation function
markov decision processes
linear combination
multiscale
case study
machine learning