An Empirical Analysis of Off-policy Learning in Discrete MDPs.

Cosmin Paduraru Doina Precup Joelle Pineau Gheorghe Comanici

Published in: EWRL (2012)

Keyphrases

reinforcement learning
learning algorithm
learning systems
learning process
prior knowledge
supervised learning
online learning
knowledge acquisition
markov decision processes
mobile devices
active learning
learning tasks
learning problems
inductive inference