Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

18

CORR
2011
Springer

favoriteEmaildiscussreport

183views Education» more CORR 2011»

Mean-Variance Optimization in Markov Decision Processes

12 years 11 months ago

Mean-Variance Optimization in Markov Decision Processes

Download web.mit.edu

We consider ﬁnite horizon Markov decision processes under performance measures that involve both the mean and the variance of the cumulative reward. We show that either randomized or history-based policies can improve performance. We prove that the complexity of computing a policy that maximizes the mean reward under a variance constraint is NP-hard for some cases, and strongly NP-hard for others. We ﬁnally offer pseudopolynomial exact and approximation algorithms.

Shie Mannor, John N. Tsitsiklis

Real-time Traffic

CORR 2011 | Cumulative Reward | Education | Horizon Markov Decision | Strongly Np-hard |

claim paper

Related Content

» Action Selection in Customer Value Optimization An Approach Based on CovariateDependent Ma...

» Eliciting Patients Revealed Preferences An Inverse Markov Decision Process Approach

» An epsilonOptimal GridBased Algorithm for Partially Observable Markov Decision Processes

» Simulationbased optimization of Markov decision processes An empirical process theory appr...

» Exact finite approximations of averagecost countable Markov decision processes

» OnLine Search for Solving Markov Decision Processes via Heuristic Sampling

» Mean field for Markov Decision Processes from Discrete to Continuous Optimization

» Perceptive Evaluation for the Optimal Discounted Reward in Markov Decision Processes

» Percentile optimization in uncertain Markov decision processes with application to efficie...

Post Info
More Details (n/a)

Added	13 May 2011
Updated	13 May 2011
Type	Journal
Year	2011
Where	CORR
Authors	Shie Mannor, John N. Tsitsiklis

Comments (0)