Simulation Based Algorithms For Markov Decision Process And Stochastic Optimization

Simulation Based Algorithms For Markov Decision Process And Stochastic Optimization

In Chapter 2, we propose several two-timescale simulation-based actor-critic algorithms for solution of infinite horizon Markov Decision Processes (MDPs) with finite state-space under the average cost criterion. On the slower timescale, all the algorithms perform a gradient search over corresponding...

Full description

Bibliographic Details
Main Author: Abdulla, Mohammed Shahid
Other Authors: Bhatnagar, Shalabh
Language:en_US
Published: 2010
Subjects:
Markov Processes - Data Processing
Algorithms
Simulation
Markov Decision Processes (MDPs)
Infinite Horizon Markov Decision Processes
Finite Horizon Markov Decision Processes
Stochastic Approximation - Algorithms
Simultaneous Perturbation Stochastic Approximation (SPSA)
Network Flow-Control
FH-MDP Algorithms
Stochastic Optimization
Reinforcement Learning Algorithms
Computational Mathematics
Online Access:http://hdl.handle.net/2005/812

Similar Items

Similar Items