# Mean-variance optimization of discrete time discounted Markov decision processes

@article{Xia2018MeanvarianceOO, title={Mean-variance optimization of discrete time discounted Markov decision processes}, author={Li Xia}, journal={Autom.}, year={2018}, volume={88}, pages={76-82} }

In this paper, we study a mean-variance optimization problem in an infinite horizon discrete time discounted Markov decision process (MDP). The objective is to minimize the variance of system rewards with the constraint of mean performance. Different from most of works in the literature which require the mean performance already achieve optimum, we can let the mean discounted performance equal any constant. The difficulty of this problem is caused by the quadratic form of the variance functionâ€¦Â Expand

#### Tables and Topics from this paper

#### 8 Citations

Risk-Sensitive Markov Decision Processes with Combined Metrics of Mean and Variance

- Computer Science, Mathematics
- ArXiv
- 2020

A New Method for Mean-Variance Optimization of Stochastic Dynamic Systems

- Computer Science
- 2019 IEEE Conference on Control Technology and Applications (CCTA)
- 2019

Optimization of Constrained Stochastic Linear-Quadratic Control on an Infinite Horizon: A Direct-Comparison Based Approach

- Computer Science
- Algorithms
- 2020

Variance-Based Risk Estimations in Markov Processes via Transformation with State Lumping

- Computer Science, Mathematics
- 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC)
- 2019

Modelling uncertainty in reinforcement learning

- Computer Science
- 2019 IEEE 58th Conference on Decision and Control (CDC)
- 2019

Multi-objective virtual network embedding algorithm based on Q-learning and curiosity-driven

- Computer Science
- EURASIP J. Wirel. Commun. Netw.
- 2018

#### References

SHOWING 1-10 OF 18 REFERENCES

Optimization of Markov decision processes under the variance criterion

- Mathematics, Computer Science
- Autom.
- 2016

Mean-Variance Criteria for Finite Continuous-Time Markov Decision Processes

- Mathematics, Computer Science
- IEEE Transactions on Automatic Control
- 2009

On the First Passage g-Mean-Variance Optimality for Discounted Continuous-Time Markov Decision Processes

- Computer Science, Mathematics
- SIAM J. Control. Optim.
- 2015

The risk probability criterion for discounted continuous-time Markov decision processes

- Mathematics, Computer Science
- Discret. Event Dyn. Syst.
- 2017

Sample-Path Optimality and Variance-Minimization of Average Cost Markov Control Processes

- Mathematics, Computer Science
- SIAM J. Control. Optim.
- 1999

The $n$th-Order Bias Optimality for Multichain Markov Decision Processes

- Mathematics, Computer Science
- IEEE Transactions on Automatic Control
- 2008