Convergence of The Relative Value Iteration for the Ergodic Control Problem of Nondegenerate Diffusions under Near-Monotone Costs
Ari ArapostathisVivek S. BorkarK. Suresh KumarPublished in: CoRR (2013)
Keyphrases
- markov chain
- human errors
- control system
- markov decision processes
- heuristic search
- control method
- neural network
- dynamic programming
- state space
- total cost
- optimal control
- convergence rate
- iterative learning control
- diffusion processes
- iterative algorithms
- boolean functions
- control strategy
- upper bound
- search algorithm
- learning algorithm