MAC With Action-Dependent State Information at One Encoder.

Lior Dikstein Haim Henri Permuter Shlomo Shamai

Published in: IEEE Trans. Inf. Theory (2015)

Keyphrases

state information
action models
action space
state space
bit rate
human actions
action selection
real valued
markov decision processes
goal directed
ai planning
partially observable
reinforcement learning
computer vision
initial state
active learning
bayesian networks