Automata theory meets approximate dynamic programming: Optimal control with temporal logic constraints.

Ivan Papusha Jie Fu Ufuk Topcu Richard M. Murray

Published in: CDC (2016)

Keyphrases

optimal control
temporal logic
approximate dynamic programming
dynamic programming
automata theory
average cost
reinforcement learning
model checking

automata theoretic
policy iteration
modal logic
dynamic constraints
linear program
actor critic
infinite horizon

control strategy
graph theory
learning theory
step size
state space
data mining
finite state

temporal difference
student learning
control policy
markov decision processes
optimal policy
artificial intelligence
machine learning