Results 71 to 80 of about 7,880,220 (196)

Planning Under Uncertainty Applications in Power Plants Using Factored Markov Decision Processes

Energies, 2020
Due to its ability to deal with non-determinism and partial observability, represent goals as an immediate reward function and find optimal solutions, planning under uncertainty using factored Markov Decision Processes (FMDPs) has increased its ...
Alberto Reyes, L. Enrique Sucar, Pablo H. Ibargüengoytia, Eduardo F. Morales   +3 more
doaj   +1 more source

Monitored Markov Decision Processes

International Joint Conference on Autonomous Agents and Multiagent Systems
In reinforcement learning (RL), an agent learns to perform a task by interacting with an environment and receiving feedback (a numerical reward) for its actions. However, the assumption that rewards are always observable is often not applicable in real-world problems. For example, the agent may need to ask a human to supervise its actions or activate a
Simone Parisi, Montaser Mohammedalamen, Alireza Kazemipour, Matthew E. Taylor, Michael Bowling   +4 more
openaire   +4 more sources

Comparing Labelled Markov Decision Processes

CoRR, 2020
35 pages, 7 ...
Stefan Kiefer, Qiyi Tang 0001
openaire   +5 more sources

Asymptotic Expansions for Moments of Hitting Times for Nonlinearly Perturbed Semi-Markov Processes

, 2017
In Chapter 3, we introduce a model of perturbed semi-Markov processes, formulate basic perturbation conditions, describe a one-step time-space screening procedure of phase space reduction for perturbed semi-Markov processes, introduce hitting times, and ...
Sergei Silvestrov, Silvestrov, Sergei,, Silvestrov, D.,, Dmitrii Silvestrov   +3 more
core   +1 more source

Communicating via Markov Decision Processes

, 2021
ICML ...
Sokota, S, de Witt, CS, Igl, M, Zintgraf, L, Torr, P, Strohmeier, M, Kolter, JZ, Whiteson, S, Foerster, J   +8 more
openaire   +4 more sources

PReMo: an analyzer for Probabilistic Recursive Models [PDF]

, 2007
This paper describes PReMo, a tool for analyzing Recursive Markov Chains, and their controlled/game extensions: (1-exit) Recursive Markov Decision Processes and Recursive Simple Stochastic ...
Dominik Wojtczak, Etessami, Kousha; id_orcid, Kousha Etessami, Wojtczak, Dominik   +3 more
core  

Mean-variance optimality for semi-Markov decision processes under first passage criteria [PDF]

, 2017
summary:This paper deals with a first passage mean-variance problem for semi-Markov decision processes in Borel spaces. The goal is to minimize the variance of a total discounted reward up to the system's first entry to some target set, where the ...
Xiangxiang Huang, Huang, Yonghui, Huang, Xiangxiang, Yonghui Huang   +3 more
core   +1 more source

Markov Decision Processing Networks

CoRR
We introduce Markov Decision Processing Networks (MDPNs) as a multiclass queueing network model where service is a controlled, finite-state Markov process. The model exhibits a decision-dependent service process where actions taken influence future service availability.
Sanidhay Bhambay, Thirupathaiah Vasantam, Neil Walton   +2 more
openaire   +2 more sources

Absorbing Markov decision processes

ESAIM: Control, Optimisation and Calculus of Variations
In this paper, we study discrete-time absorbing Markov Decision Processes (MDP) with measurable state space and Borel action space with a given initial distribution. For such models, solutions to the characteristic equation that are not occupation measures may exist.
Dufour, François, Prieto-Rumeau, Tomás
openaire   +3 more sources

Bounds for Synchronizing Markov Decision Processes

, 2022
We consider Markov decision processes with synchronizing objectives, which require that a probability mass of $1-ε$ accumulates in a designated set of target states, either once, always, infinitely often, or always from some point on, where $ε= 0$ for sure synchronizing, and $ε\to 0$ for almost-sure and limit-sure synchronizing.
Doyen, Laurent, van den Bogaard, Marie
openaire   +3 more sources