Markov decision processes and stochastic games with total effective payoff
نویسندگان
چکیده
منابع مشابه
Markov Decision Processes and Stochastic Games with Total Effective Payoff
We consider finite Markov decision processes (MDPs) with undiscounted total effective payoff. We show that there exist uniformly optimal pure stationary strategies that can be computed by solving a polynomial number of linear programs. We apply this result to two-player zero-sum stochastic games with perfect information and undiscounted total effective payoff, and derive the existence of a sadd...
متن کاملMarkov Decision Processes and Stochastic Games with Total Effective Payoff a
We consider finite Markov decision processes (MDPs) with undiscounted total effective payoff. We show that there exist uniformly optimal pure stationary strategies that can be computed by solving a polynomial number of linear programs. We apply this result to two-player zero-sum stochastic games with perfect information and undiscounted total effective payoff, and derive the existence of a sadd...
متن کاملStochastic Scheduling Games with Markov Decision Arrival Processes
In Hordijk & Koole [4,5] a new type of arrival process, the Markov Decision Arrival Process (MDAP), was introduced which can be used to model certain dependencies between arrival streams and the system at which the arrivals occur. This arrival process was used to solve control problems with several controllers having a common objective, where the output from one controlled node is fed into a se...
متن کاملGames and Markov Decision Processes with Mean-Payoff Parity and Energy Parity Objectives
In this paper we survey results of two-player games on graphs and Markov decision processes with parity, mean-payoff and energy objectives, and the combination of mean-payoff and energy objectives with parity objectives. These problems have applications in verification and synthesis of reactive systems in resource-constrained environments.
متن کاملOnline Learning in Stochastic Games and Markov Decision Processes
In their standard formulations, stochastic games and Markov decision processes assume a rational opponent or a stationary environment. Online learning algorithms can adapt to arbitrary opponents and non-stationary environments, but do not incorporate the dynamic structure of stochastic games or Markov decision processes. We survey recent approaches that apply online learning to dynamic environm...
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: Annals of Operations Research
سال: 2018
ISSN: 0254-5330,1572-9338
DOI: 10.1007/s10479-018-2898-8