On the convergence of projective-simulation-based reinforcement learning in Markov decision processes. [PDF]
Quantum Mach Intell, 2020 Boyajian WL +4 more
europepmc +1 more source
Dealing with non-stationarity in Constrained Markov Decision Processes [PDF]
LAUREA MAGISTRALENei Processi Decisionali di Markov Vincolati (Constrained Markov Decision Processes o CMDP) con ricompense e vincoli avversari, un noto risultato di impossibilità impedisce a qualsiasi algoritmo di ottenere sia un regret sublineare che ...
Lunghi, Anna
core
Robustness to Modeling Errors in Risk-Sensitive Markov Decision Problems With Markov Risk Measures
IEEE Open Journal of Control SystemsWe consider risk-sensitive Markov decision processes (MDPs), where the MDP model is influenced by a parameter which takes values in a compact metric space. These situations arise when the underlying dynamics of the system depend on parameters that drifts
Shiping Shao, Abhishek Gupta
doaj +1 more source
On Markov Chains with Uncertain Data [PDF]
In this paper, a general method is described to determine uncertainty intervals for performance measures of Markov chains given an uncertainty region for the parameters of the Markov chains.
Blanc, J.P.C., Hertog, D. den
core
Non-Stationary Markov Decision Processes a Worst-Case Approach using Model-Based Reinforcement Learning [PDF]
, 2019 This work tackles the problem of robust zero-shot planning in non-stationary stochastic environments. We study Markov Decision Processes (MDPs) evolving over time and consider Model-Based Reinforcement Learning algorithms in this setting.
Lecarpentier, Erwan, Rachelson, Emmanuel
core
Online learning in stochastic and adversarial constrained Markov decision processes [PDF]
LAUREA MAGISTRALEI moderni processi decisionali richiedono sempre più spesso la capacità di adattarsi a contesti incerti e dinamici, le cui condizioni non sono note in anticipo e possono evolvere in modo imprevedibile nel tempo.
CHIEFARI, ELEONORA FIDELIA
core
Modelling the purchase dynamics of insurance customers using Markov chains
, 2005 This paper considers how various types of Markov chains can be used to help forecast the purchase behaviour of customers. The models are used in a case study of the purchase behaviour of the customers of a major insurance company.
Thomas, Lyn C. +3 more
core +1 more source
Optimizing genomic sampling for demographic and epidemiological inference with Markov decision processes. [PDF]
GeneticsRasmussen DA, Bursell MG, Burkhart F.
europepmc +1 more source
On A Markov Game with Incomplete Information [PDF]
We consider an example of a Markov game with lack of information on one side, that was first introduced by Renault (2002). We compute both the value and optimal strategies for a range of parameter values.
Dinah Rosenberg +3 more
core
Strategic cancer therapy planning: optimizing treatment and quality of life with Markov decision processes. [PDF]
Rep Pract Oncol RadiotherSingh S +5 more
europepmc +1 more source