We characterize the reachability probabilities in stochastic directed graphs by means of reinforcement learning methods. In particular, we show that the dynamics of the transition probabilities in a stochastic digraph can be modeled via a difference inclusion, which, in turn, can be interpreted as a Markov decision process. Using the latter framework, we offer a methodology to design reward functions to provide upper and lower bounds on the reachability probabilities of a set of nodes for stochastic digraphs. The effectiveness of the proposed technique is demonstrated by application to the diffusion of epidemic diseases over time-varying contact networks generated by the proximity patterns of mobile agents.

Reachability analysis in stochastic directed graphs by reinforcement learning / Possieri, C.; Frasca, M.; Rizzo, A.. - In: IEEE TRANSACTIONS ON AUTOMATIC CONTROL. - ISSN 1558-2523. - ELETTRONICO. - 68:1(2023), pp. 462-469. [10.1109/TAC.2022.3143080]

Reachability analysis in stochastic directed graphs by reinforcement learning

Rizzo, A.
2023

Abstract

We characterize the reachability probabilities in stochastic directed graphs by means of reinforcement learning methods. In particular, we show that the dynamics of the transition probabilities in a stochastic digraph can be modeled via a difference inclusion, which, in turn, can be interpreted as a Markov decision process. Using the latter framework, we offer a methodology to design reward functions to provide upper and lower bounds on the reachability probabilities of a set of nodes for stochastic digraphs. The effectiveness of the proposed technique is demonstrated by application to the diffusion of epidemic diseases over time-varying contact networks generated by the proximity patterns of mobile agents.
File in questo prodotto:
File Dimensione Formato  
2023_PFR_TAC_Graphs_AuthorPostprint.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Pubblico - Tutti i diritti riservati
Dimensione 438.69 kB
Formato Adobe PDF
438.69 kB Adobe PDF Visualizza/Apri
2023_TAC_Reachability_Analysis_in_Stochastic_Directed_Graphs_by_Reinforcement_Learning.pdf

accesso riservato

Descrizione: Version of record
Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 548.88 kB
Formato Adobe PDF
548.88 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2957678