no code implementations • 24 Apr 2018 • Jan Křetínský, Guillermo A. Pérez, Jean-François Raskin
Assuming the support of the unknown transition function and a lower bound on the minimal transition probability are known in advance, we show that in MDPs consisting of a single end component, two combinations of guarantees on the parity and mean-payoff objectives can be achieved depending on how much memory one is willing to use.
no code implementations • 17 Feb 2017 • Raphaël Berthon, Mickael Randour, Jean-François Raskin
We establish that, for all variants of this problem, deciding the existence of a strategy lies in ${\sf NP} \cap {\sf coNP}$, the same complexity class as classical parity games.
no code implementations • 25 Jan 2020 • Gavin Rens, Jean-François Raskin
There are situations in which an agent should receive rewards only after having accomplished a series of previous tasks.
no code implementations • 28 Apr 2020 • Raphaël Berthon, Shibashis Guha, Jean-François Raskin
In this paper, we consider algorithms to decide the existence of strategies in MDPs for Boolean combinations of objectives.
no code implementations • 19 May 2020 • Damien Busatto-Gaston, Debraj Chakraborty, Shibashis Guha, Guillermo A. Pérez, Jean-François Raskin
In this paper, we investigate the combination of synthesis, model-based learning, and online sampling techniques to obtain safe and near-optimal schedulers for a preemptible task scheduling problem.
no code implementations • 26 Sep 2020 • Gavin Rens, Jean-François Raskin, Raphaël Reynouad, Giuseppe Marra
In our formal setting, we consider a Markov decision process (MDP) that models the dynamics of the environment in which the agent evolves and a Mealy machine synchronized with this MDP to formalize the non-Markovian reward function.
no code implementations • 17 Feb 2021 • Véronique Bruyère, Jean-François Raskin, Clément Tamines
In this paper, we study the framework of two-player Stackelberg games played on graphs in which Player 0 announces a strategy and Player 1 responds rationally with a strategy that is an optimal response.
Computer Science and Game Theory
no code implementations • 23 Apr 2021 • Raphaël Berthon, Adrien Boiret, Guillermo A. Perez, Jean-François Raskin
We show that there exists an algorithm using string equation solvers that uses this knowledge to learn subsequential string transducers with a better guarantee on the required number of equivalence queries than classical active learning.
no code implementations • 22 Jun 2021 • Wen-Chi Yang, Jean-François Raskin, Luc De Raedt
We present pCTL-REBEL, a lifted model checking approach for verifying pCTL properties of relational MDPs.
Model-based Reinforcement Learning reinforcement-learning +1
no code implementations • 7 Nov 2022 • Gavin Rens, Wen-Chi Yang, Jean-François Raskin, Luc De Raedt
The task then consists of learning this unknown formula from states that are labeled as safe or unsafe by a domain expert.
no code implementations • 15 Aug 2023 • Debraj Chakraborty, Damien Busatto-Gaston, Jean-François Raskin, Guillermo A. Pérez
In particular, we use model-checking techniques to guide the MCTS algorithm in order to generate offline samples of high-quality decisions on a representative set of states of the MDP.
1 code implementation • 26 Nov 2016 • Krishnendu Chatterjee, Petr Novotný, Guillermo A. Pérez, Jean-François Raskin, Đorđe Žikelić
In this work we go beyond both the "expectation" and "threshold" approaches and consider a "guaranteed payoff optimization (GPO)" problem for POMDPs, where we are given a threshold $t$ and the objective is to find a policy $\sigma$ such that a) each possible outcome of $\sigma$ yields a discounted-sum payoff of at least $t$, and b) the expected discounted-sum payoff of $\sigma$ is optimal (or near-optimal) among all policies satisfying a).