|
DRUM >
Institute for Systems Research >
Institute for Systems Research Technical Reports >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/1903/6029
|
| Title: | Simulation-Based Algorithms for Average Cost Markov Decision Processes |
| Authors: | He, Ying
Fu, Michael C.
Marcus, Steven I. |
| Advisors: | Fu, Michael C.
Marcus, Steven I. |
| Department/Program: | ISR |
| Type: | Technical Report |
| Keywords: | algorithms, Simulation-Based Policy Iteration, Simulation-Based Value Iteration, Markov Decision Processes, Average Cost, Unichain, Systems Integration Methodology |
| Issue Date: | 1999 |
| Series/Report no.: | ISR; TR 1999-56 |
| Abstract: | In this paper, we give a summary of recent development of simulation-based algorithmsfor average cost MDP problems, which are different from those for discounted cost problems or shortest pathproblems. We introduce both simulation-based policy iteration algorithms and simulation-based value iterationalgorithms for average cost problems, and give the pros and cons of each algorithm. |
| URI: | http://hdl.handle.net/1903/6029 |
| Appears in Collections: | Institute for Systems Research Technical Reports
|
All items in DRUM are protected by copyright, with all rights reserved.
|
