Results 101 to 110 of about 7,880,220 (196)

Policy Iteration for Continuous-Time Average Reward Markov Decision Processes in Polish Spaces

Abstract and Applied Analysis, 2009
We study the policy iteration algorithm (PIA) for continuous-time jump Markov decision processes in general state and action spaces. The corresponding transition rates are allowed to be unbounded, and the reward rates may have neither upper nor lower ...
Quanxin Zhu, Xinsong Yang, Chuangxia Huang   +2 more
doaj   +1 more source

Strong average optimality criterion for continuous-time Markov decision processes [PDF]

, 2014
summary:This paper deals with continuous-time Markov decision processes with the unbounded transition rates under the strong average cost criterion. The state and action spaces are Borel spaces, and the costs are allowed to be unbounded from above and ...
Chen, Xian, Wei, Qingda
core   +1 more source

Control Design for Untimed Petri Nets Using Markov Decision Processes

Operations Research and Decisions, 2017
Design of control sequences for discrete event systems (DESs) has been presented modelled by untimed Petri nets (PNs). PNs are well-known mathematical and graphical models that are widely used to describe distributed DESs, including choices ...
Cherki Daoui, Dimitri Lefebvre
doaj  

The existence and characterisation of duality of Markov processes in the Euclidean space [PDF]

This thesis examines the existence of dualMarkov processes and presents the full characterization of Markov processes in Euclidean space equipped with the natural order (the Pareto order).
Lee, Rui Xin
core  

Fuel in Markov Decision Processes (FiMDP): A Practical Approach to Consumption. [PDF]

FME, 2021
Blahoudek F, Cubuktepe M, Novotný P, Ornik M, Thangeda P, Topcu U.   +5 more
europepmc   +1 more source

On incorporating forecasts into linear state space model Markov decision processes. [PDF]

Philos Trans A Math Phys Eng Sci, 2021
de Chalendar JA, Glynn PW.
europepmc   +1 more source

Learning parametric policies and transition probability models of markov decision processes from data. [PDF]

Eur J Control, 2021
Xu T, Zhu H, Paschalidis IC.
europepmc   +1 more source

Counterfactual Strategies for Markov Decision Processes

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence
Counterfactuals are widely used in AI to explain how minimal changes to a model’s input can lead to a different output. However, established methods for computing counterfactuals typically focus on one-step decision-making, and are not directly applicable to sequential decision-making tasks.
Kobialka, Paul, Gerlach, Carolina, Leofante, Francesco, Ábrahám, Erika, Lizeth, Silvia, Tarifa, Tapia, Johnsen, Einar Brocj   +6 more
openaire   +5 more sources

Differentially Private Reward Functions in Markov Decision Processes: Policy Synthesis and Tradeoffs

IEEE Open Journal of Control Systems
Policy synthesis in Markov decision processes uses a known reward function to compute a policy that maximizes it. However, onlookers may infer reward functions by observing agents, which can reveal sensitive information.
Alexander Benvenuti, Calvin Hawkins, Brandon Fallin, Bo Chen, Brendan Bialy, Miriam Dennis, Matthew T. Hale   +6 more
doaj   +1 more source

Data-Driven Synthesis of Probabilistic Controlled Invariant Sets for Linear Markov Decision Processes

IEEE Open Journal of Control Systems
We study data-driven computation of probabilistic controlled invariant sets (PCIS) for safety-critical reinforcement learning under unknown dynamics. Assuming a linear MDP model, we use regularized least squares and self-normalized confidence bounds to ...
Kazumune Hashimoto, Shunki Kimura, Junya Ikemoto, Kazunobu Serizawa, Yulong Gao, Kai Cai   +5 more
doaj   +1 more source