Search engine for discovering works of Art, research articles, and books related to Art and Culture
ShareThis
Javascript must be enabled to continue!

No good Markov strategies for Büchi objectives in countable MDPs

View through CrossRef
Abstract We study countably infinite Markov decision processes with Büchi objectives, which ask to visit a given subset of states infinitely often. A question left open by T.P. Hill (1979) is whether there always exist $$\varepsilon $$ ε -optimal Markov strategies, i.e., strategies that base decisions only on the current state and on the clock (the number of steps taken so far). We provide a negative answer to this question by constructing a non-trivial counterexample.
Title: No good Markov strategies for Büchi objectives in countable MDPs
Description:
Abstract We study countably infinite Markov decision processes with Büchi objectives, which ask to visit a given subset of states infinitely often.
A question left open by T.
P.
Hill (1979) is whether there always exist $$\varepsilon $$ ε -optimal Markov strategies, i.
e.
, strategies that base decisions only on the current state and on the clock (the number of steps taken so far).
We provide a negative answer to this question by constructing a non-trivial counterexample.

Related Results

Developing Optimal Decision Strategies with Markovian Decision Process
Developing Optimal Decision Strategies with Markovian Decision Process
The use of Markovian Decision Processes (MDPs) in creating the best possible decision strategies is examined in this research. When outcomes are partly controlled by a decision-mak...
Optimal policy analysis for monotonic (PO)MDPs and an application to fishery management
Optimal policy analysis for monotonic (PO)MDPs and an application to fishery management
Abstract We study the monotonicity properties of optimal policies for a class of fully/partially observable Markov Decision Processes (MDPs) motivated by renewable natural ...
Digestibilidade e degradabilidade de rações à base de milho desintegrado com palha e sabugo em diferentes graus de moagem
Digestibilidade e degradabilidade de rações à base de milho desintegrado com palha e sabugo em diferentes graus de moagem
O objetivo deste trabalho foi determinar a digestibilidade, usando óxido crômico (Cr2O3) e FDN indigestível, como indicadores, e a degradação de dietas compostas de milho desintegr...
J. Richard Büchi
J. Richard Büchi
Abstract Julius Richard Büchi was born in Porto Allegre, Brazil, on 31 January 1924 to Swiss parents and as a citizen of Zell, Switzerland. He grew up in Switzerland...
Solving MDPs with Unknown Rewards Using Nondominated Vector-Valued Functions
Solving MDPs with Unknown Rewards Using Nondominated Vector-Valued Functions
This paper addresses vectorial form of Markov Decision Processes (MDPs) to solve MDPs with unknown rewards. Our method to find optimal strategies is based on reducing the computati...
ANALISA PERBANDINGAN METODE CELLULAR AUTOMATA ANN DAN MARKOV UNTUK PREDIKSI TUTUPAN LAHAN DI KOTA BLITAR
ANALISA PERBANDINGAN METODE CELLULAR AUTOMATA ANN DAN MARKOV UNTUK PREDIKSI TUTUPAN LAHAN DI KOTA BLITAR
ABSTRACT The development of urban areas in Blitar City, which is triggered by population growth and mobility, has caused changes in land cover, especially the reduction in rice fie...

Back to Top