Average Cost Optimal Control of Stochastic Systems Using Reinforcement Learning.

Jing Lai Junlin Xiong

Published in: CoRR (2020)

Keyphrases

optimal control
average cost
stochastic systems
reinforcement learning
infinite horizon
control problems
approximate dynamic programming

stochastic models
dynamic programming
finite horizon
risk sensitive
function approximation
markov decision processes
state space

control strategy
control law
confidence intervals
initial state
control policy
markov decision process
optimal policy

policy iteration
stochastic processes
holding cost
control system
markov decision problems
partially observable
temporal difference