Sign in
Information-Theoretic Methods for Planning and Learning in Partially Observable Markov Decision Processes.
Roy Fox
Published in:
CoRR (2016)
Keyphrases
</>
information theoretic
stochastic domains
entropy measure
reinforcement learning
mutual information
information bottleneck
information theory
learning algorithm
state space
planning problems
kullback leibler divergence
information theoretic measures
text categorization
domain independent
partially observable