On the reduction of total‐cost and average‐cost MDPs to discounted MDPs
نویسندگان
چکیده
منابع مشابه
On the Reduction of Total-Cost and Average-Cost MDPs to Discounted MDPs
This paper provides conditions under which total-cost and average-cost Markov decision processes (MDPs) can be reduced to discounted ones. Results are given for transient total-cost MDPs with transition rates whose values may be greater than one, as well as for average-cost MDPs with transition probabilities satisfying the condition that there is a state such that the expected time to reach it ...
متن کاملPAC Bounds for Discounted MDPs
We study upper and lower bounds on the sample-complexity of learning nearoptimal behaviour in finite-state discounted Markov Decision Processes (mdps). We prove a new bound for a modified version of Upper Confidence Reinforcement Learning (ucrl) with only cubic dependence on the horizon. The bound is unimprovable in all parameters except the size of the state/action space, where it depends line...
متن کاملReduction of Discounted Continuous-Time MDPs with Unbounded Jump and Reward Rates to Discrete-Time Total-Reward MDPs
This article discusses a reduction of discounted Continuous-Time Markov Decision Processes (CTMDPs) to discrete-time Markov Decision Processes (MDPs). This reduction is based on the equivalence of a randomized policy that chooses actions only at jump epochs to a nonrandomized policy that can switch actions between jumps. For discounted CTMDPs with bounded jump rates, this reduction was introduc...
متن کاملNear-optimal PAC bounds for discounted MDPs
We study upper and lower bounds on the sample-complexity of learning near-optimal behaviour in finite-state discounted Markov Decision Processes (MDPs). We prove a new bound for a modified version of Upper Confidence Reinforcement Learning (UCRL) with only cubic dependence on the horizon. The bound is unimprovable in all parameters except the size of the state/action space, where it depends lin...
متن کاملMulti-objective Discounted Reward Verification in Graphs and MDPs
We study the problem of achieving a given value in Markov decision processes (MDPs) with several independent discounted reward objectives. We consider a generalised version of discounted reward objectives, in which the amount of discounting depends on the states visited and on the objective. This definition extends the usual definition of discounted reward, and allows to capture the systems in ...
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: Naval Research Logistics (NRL)
سال: 2017
ISSN: 0894-069X,1520-6750
DOI: 10.1002/nav.21743