Strength calculation of rewards.

Mariela Morveli Espinoza Ayslan Trevizan Possebom Cesar A. Tacla

Published in: CMNA@IJCAI (2016)

Keyphrases

reinforcement learning
multiarmed bandit
databases
bandit problems
cooperative
pairwise
markov decision processes
multi armed bandits
real time
e learning
decision trees
calculation method