Mean-variance tradeoffs in an undiscounted MDP: The unichain case

Mean-variance tradeoffs in an undiscounted MDP: The unichain case

0.00 Avg rating0 Votes
Article ID: iaor1995334
Country: United States
Volume: 42
Issue: 1
Start Page Number: 184
End Page Number: 188
Publication Date: Jan 1994
Journal: Operations Research
Authors:
Keywords: decision theory, programming: dynamic
Abstract:

The problem analyzed here is the computation of Pareto optima in the sense of high mean and low variance of the stationary distribution in the unichain undiscounted Markov decision process (MDP).

Reviews

Required fields are marked *. Your email address will not be published.