System identification with binary observations by stochastic approximation and active learning.

Balázs Csanád Csáji Erik Weyer

Published in: CDC/ECC (2011)

Keyphrases

stochastic approximation
active learning
monte carlo
policy iteration
learning algorithm
labeled data
machine learning
semi supervised
linear programming
temporal difference learning
reinforcement learning
training set
artificial neural networks
learning process
optical flow
markov decision processes