ELL729
| ELL729 | |
|---|---|
| Stochastic Control and Reinforcement Learning | |
| Credits | 3 |
| Structure | 3-0-0 |
| Pre-requisites | |
| Overlaps | |
ELL729 : Stochastic Control and Reinforcement Learning
[edit]Basics of dynamic programming, Finite horizon MDP with quadratic cost, Optimal stopping problems, Partially observable MDP, Infinite horizon discounted cost problems, Stochastic shortest path problems, Undiscounted cost problems, Average cost problems, Semi-Markov decision process, Constrained MDP, Basics of stochastic approximation, Kiefer-Wolfowitz algorithm, Simultaneous perturbation stochastic approximation, Q learning and its convergence analysis.