Login / Signup
Data-Efficient Reinforcement Learning in Continuous-State POMDPs.
Rowan McAllister
Carl Edward Rasmussen
Published in:
CoRR (2016)
Keyphrases
</>
reinforcement learning
continuous state
markov decision processes
function approximation
robot navigation
state space
domain specific
bayesian networks
search space
probability distribution
optimal control
partially observable markov decision processes