Login / Signup
MAC with Action-Dependent State Information at One Encoder
Lior Dikstein
Haim H. Permuter
Shlomo Shamai
Published in:
CoRR (2012)
Keyphrases
</>
state information
action models
action space
state space
human actions
transfer learning
goal directed
real valued
reinforcement learning
ai planning
partially observable
stochastic processes
bit rate
dynamic programming
markov decision processes
initial state
domain specific