Efficient approximation of optimal control for continuous-time Markov games.

John Fearnley Markus N. Rabe Sven Schewe Lijun Zhang

Published in: Inf. Comput. (2016)

Keyphrases

optimal control
control problems
markov games
optimal control problems
dynamic programming
control strategy
infinite horizon
reinforcement learning
brownian motion
control law
reinforcement learning algorithms
state space
multistage
markov decision processes
differential equations
average cost
np hard