Distribution-based objectives for Markov Decision Processes
| Autor: | Sundararaman Akshay, Blaise Genest, Nikhil Vyas |
|---|---|
| Přispěvatelé: | Indian Institute of Technology Bombay (IIT Bombay), Université de Rennes (UR), SUpervision of large MOdular and distributed systems (SUMO), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-LANGAGE ET GÉNIE LOGICIEL (IRISA-D4), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Massachusetts Institute of Technology (MIT), equipe associée / project CEFIPRA EQUAVE, ANR-13-BS02-0011,Stoch-MC,Modèles stochastiques: passage à l'échelle pour le Model Checking(2013), Université de Rennes (UNIV-RENNES), Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique) |
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: |
Discrete mathematics
FOS: Computer and information sciences Computer Science - Logic in Computer Science Discrete Mathematics (cs.DM) Computer science Existential quantification EXPTIME [INFO.INFO-OH]Computer Science [cs]/Other [cs.OH] Context (language use) 0102 computer and information sciences 02 engineering and technology Computational Complexity (cs.CC) 01 natural sciences Decidability Undecidable problem Logic in Computer Science (cs.LO) Computer Science - Computational Complexity 010201 computation theory & mathematics Convex polytope 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Markov decision process Computer Science - Discrete Mathematics |
| Zdroj: | LICS 2018, the 33rd Annual ACM/IEEE Symposium LICS 2018, the 33rd Annual ACM/IEEE Symposium, Jul 2018, Oxford, United Kingdom. pp.36-45, ⟨10.1145/3209108.3209185⟩ LICS |
| Popis: | We consider distribution-based objectives for Markov Decision Processes (MDP). This class of objectives gives rise to an interesting trade-off between full and partial information. As in full observation, the strategy in the MDP can depend on the state of the system, but similar to partial information, the strategy needs to account for all the states at the same time. In this paper, we focus on two safety problems that arise naturally in this context, namely, existential and universal safety. Given an MDP A and a closed and convex polytope H of probability distributions over the states of A, the existential safety problem asks whether there exists some distribution d in H and a strategy of A, such that starting from d and repeatedly applying this strategy keeps the distribution forever in H. The universal safety problem asks whether for all distributions in H, there exists such a strategy of A which keeps the distribution forever in H. We prove that both problems are decidable, with tight complexity bounds: we show that existential safety is PTIME-complete, while universal safety is co-NP-complete. Further, we compare these results with existential and universal safety problems for Rabin's probabilistic finite-state automata (PFA), the subclass of Partially Observable MDPs which have zero observation. Compared to MDPs, strategies of PFAs are not state-dependent. In sharp contrast to the PTIME result, we show that existential safety for PFAs is undecidable, with H having closed and open boundaries. On the other hand, it turns out that the universal safety for PFAs is decidable in EXPTIME, with a co-NP lower bound. Finally, we show that an alternate representation of the input polytope allows us to improve the complexity of universal safety for MDPs and PFAs. Comment: An extended abstract of this paper has been accepted in the conference LICS'2018 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|