A feature selection method for a sample-based stochastic policy.

Jumpei Yamanaka Yutaka Nakamura Hiroshi Ishiguro

Published in: Artif. Life Robotics (2014)

Keyphrases

optimal policy
control policies
state dependent
model free reinforcement learning
monte carlo
asymptotically optimal
stochastic nature
database
stochastic model
randomly selected
neural network
stochastic process
learning automata
stochastic optimization
sample points
probability distribution
real time