Continuous time control of Markov processes on an arbitrary state space: Average return criterion
نویسندگان
چکیده
منابع مشابه
Nonparametric Adaptive Control for Discrete - Time Markov Processes with Unbounded Costs under Average Criterion
We introduce average cost optimal adaptive policies in a class of discrete-time Markov control processes with Borel state and action spaces, allowing unbounded costs. The processes evolve according to the system equations xt+1 = F (xt, at, ξt), t = 1, 2, . . . , with i.i.d. R -valued random vectors ξt, which are observable but whose density ̺ is unknown.
متن کاملOn Continuous Time Markov Games with Countable State Space
This paper is a continuation of our papers [61 and [71 and is concerned with a continuous time Markov game in which the state space is countable and the action spaces of player I and player n are compact metric spaces. In the game, the players continuously observe the state of the system and then choose actions. As a result, the reward is paid to player I from player n and the system moves to a...
متن کاملDrift and monotonicity conditions for continuous-time controlled Markov chains with an average criterion
In this paper, we give conditions for the existence of average optimal policies for continuous-time controlled Markov chains with a denumerable state–space and Borel action sets. The transition rates are allowed to be unbounded, and the reward/cost rates may have neither upper nor lower bounds. In the spirit of the “drift and monotonicity” conditions for continuous-time Markov processes, we pro...
متن کاملOPTIMAL CONTROL OF AVERAGE REWARD MARKOV DECISION PROCESSES ' CONSTRAINED CONTINUOUS - TIME FINITE Eugene
The paper studies optimization of average-reward continuous-time finite state and action Markov Decision Processes with multiple criteria and constraints. Under the standard unichain assumption, we prove the existence of optimal K-switching strategies for feasible problems with K constraints. For switching randomized strategies, the decisions depend on the current state and the the time spent i...
متن کاملOn Markov Chains with Continuous State Space
In this expository paper, we p r o ve the following theorem, which m a y be of some use in studying Markov chain Monte Carlo methods like hit and run, the Metropolis algorithm, or the Gibbs sampler. Suppose a discrete-time Markov c hain is aperiodic, irreducible, and there is a stationary probability distribution. Then from almost all starting points the distribution of the chain at time n conv...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Stochastic Processes and their Applications
سال: 1976
ISSN: 0304-4149
DOI: 10.1016/0304-4149(76)90026-0