More or Less True DCTL for Continuous-Time MDPs.

David N. Jansen

Published in: FORMATS (2013)

Keyphrases

markov decision processes
state space
reinforcement learning
factored mdps
dynamic programming
linear programming
optimal policy
optimal control
average cost
stochastic processes
markov decision process
finite state
markov processes
markov decision problems
continuous state spaces
semi markov decision processes