Approximate dynamic programming for stochastic reachability.

Nikolaos Kariotoglou Sean Summers Tyler H. Summers Maryam Kamgarpour John Lygeros

Published in: ECC (2013)

Keyphrases

approximate dynamic programming
stochastic dynamic programming
linear program
dynamic programming
reinforcement learning
state space
step size
factored mdps
monte carlo
control policy
average cost
linear programming
np hard
least squares
policy iteration
control policies