Convergence Analysis of Control Optimization Methods
- 1k Downloads
This chapter will discuss the proofs of optimality of most of the algorithms discussed in the context of control optimization. Since all the related algorithms are iterative and generate sequences of values, we will be dealing with convergence of these sequences to optimal solutions.
KeywordsOptimal Policy Bellman Equation Policy Iteration Average Reward Discount Reward
Unable to display preview. Download preview PDF.