Partially Observable Markov Decision Processes (POMDPs) model sequential decision-making problems under uncertainty and partial observability. Unfortunately, some problems cannot be modeled with state-dependent reward functions, e.g., problems whose objective explicitly implies reducing the uncertainty on the state. To that end, we introduce ρPOMDPs, an extension of POMDPs where the reward function ρ depends on the belief state. We show that, under the common assumption that ρ is convex, the value function is also convex, what makes it possible to (1) approximate ρ arbitrarily well with a piecewise linear and convex (PWLC) function, and (2) use state-of-the-art exact or approximate solving algorithms with limited changes.Les processus de dé...
Given a growing sequence of observations x_1,...,x_n,..., one is required, at each time step n, to m...
National audienceRésoudre optimalement des processus décisionnels de Markov partiellement observable...
We study stochastic control applications to real options and to liquidity risk model. More precisely...
Decentralized partially observable Markov decision processes (Dec-POMDPs) provide a general model fo...
International audienceDans cet article, nous nous intéressons à la résolution de problèmes de collec...
Bandits are one of the most basic examples of decision-making with uncertainty. A Markovian restless...
Co-encadrement de la thèse : Marc Bordier et Jean-Paul MarmoratAbstract: A way to improve an existin...
We investigate different ways of generating approximate solutions to the inverse problem of pairwise...
Rigorous numerics aims at providing certified representations for solutions of various problems, not...
We study classical statistical problems such as as community detection on graphs, Principal Componen...
For certain physical phenomenon that are modelled by PDE, the coefficients intervening in the equati...
National audienceSolving a 2-player zero-sum partially observable stochastic game (zs-POSG) typicall...
The pinning model describes the behavior of a Markov chain in interaction with a distinguished state...
The work reported in this thesis revisits in two waysthe abstract domain of polyhedraused for static...
Trustworthiness in systems is of paramount importance. Among safety modeling languages, Markov chain...
Given a growing sequence of observations x_1,...,x_n,..., one is required, at each time step n, to m...
National audienceRésoudre optimalement des processus décisionnels de Markov partiellement observable...
We study stochastic control applications to real options and to liquidity risk model. More precisely...
Decentralized partially observable Markov decision processes (Dec-POMDPs) provide a general model fo...
International audienceDans cet article, nous nous intéressons à la résolution de problèmes de collec...
Bandits are one of the most basic examples of decision-making with uncertainty. A Markovian restless...
Co-encadrement de la thèse : Marc Bordier et Jean-Paul MarmoratAbstract: A way to improve an existin...
We investigate different ways of generating approximate solutions to the inverse problem of pairwise...
Rigorous numerics aims at providing certified representations for solutions of various problems, not...
We study classical statistical problems such as as community detection on graphs, Principal Componen...
For certain physical phenomenon that are modelled by PDE, the coefficients intervening in the equati...
National audienceSolving a 2-player zero-sum partially observable stochastic game (zs-POSG) typicall...
The pinning model describes the behavior of a Markov chain in interaction with a distinguished state...
The work reported in this thesis revisits in two waysthe abstract domain of polyhedraused for static...
Trustworthiness in systems is of paramount importance. Among safety modeling languages, Markov chain...
Given a growing sequence of observations x_1,...,x_n,..., one is required, at each time step n, to m...
National audienceRésoudre optimalement des processus décisionnels de Markov partiellement observable...
We study stochastic control applications to real options and to liquidity risk model. More precisely...