Robustness to Incorrect Models in Average-Cost Optimal Stochastic Control.

Ali Devran Kara Maxim Raginsky Serdar Yüksel

Published in: CDC (2019)

Keyphrases

average cost
optimal control
stochastic control
long run
markov decision processes
dynamic programming
markov decision chains
queueing systems
finite number
closed form
control system
reinforcement learning
multistage
optimal policy
infinite horizon
linear programming
finite horizon
real time