Target-sensitive control of Markov and semi-Markov processes
نویسنده
چکیده
We develop the theory for Markov and semi-Markov control using dynamic programming and reinforcement learning in which a form of semi-variance which computes the variability of rewards below a pre-specified target is penalized. The objective is to optimize a function of the rewards and risk where risk is penalized. Penalizing variance, which is popular in the literature, has some drawbacks that can be avoided with semi-variance.
منابع مشابه
Forecasting time and place of earthquakes using a Semi-Markov model (with case study in Tehran province)
The paper examines the application of semi-Markov models to the phenomenon of earthquakes in Tehran province. Generally, earthquakes are not independent of each other, and time and place of earthquakes are related to previous earthquakes; moreover, the time between earthquakes affects the pattern of their occurrence; thus, this occurrence can be likened to semi-Markov models. ...
متن کاملApplying Semi-Markov Models for forecasting the Triple Dimensions of Next Earthquake Occurrences: with Case Study in Iran Area
In this paper Semi-Markov models are used to forecast the triple dimensions of next earthquake occurrences. Each earthquake can be investigated in three dimensions including temporal, spatial and magnitude. Semi-Markov models can be used for earthquake forecasting in each arbitrary area and each area can be divided into several zones. In Semi-Markov models each zone can be considered as a sta...
متن کاملExpected Duration of Dynamic Markov PERT Networks
Abstract : In this paper , we apply the stochastic dynamic programming to approximate the mean project completion time in dynamic Markov PERT networks. It is assumed that the activity durations are independent random variables with exponential distributions, but some social and economical problems influence the mean of activity durations. It is also assumed that the social problems evolve in ac...
متن کاملOn $L_1$-weak ergodicity of nonhomogeneous continuous-time Markov processes
In the present paper we investigate the $L_1$-weak ergodicity of nonhomogeneous continuous-time Markov processes with general state spaces. We provide a necessary and sufficient condition for such processes to satisfy the $L_1$-weak ergodicity. Moreover, we apply the obtained results to establish $L_1$-weak ergodicity of quadratic stochastic processes.
متن کامل