Partially Observable Monte-Carlo Planning (POMCP) is a powerful online algorithm that can generate online policies for large Partially Observable Markov Decision Processes. The lack of an explicit representation of the policy, however, hinders interpretability. In this work, we present a MAX-SMT based methodology to iteratively explore local properties of the policy. Our approach generates a compact and informative representation that describes the system under investigation.

Policy Interpretation for Partially Observable Monte-Carlo Planning: A Rule-Based Approach

G. Mazzi;A. Castellini;A. Farinelli
2021

Abstract

Partially Observable Monte-Carlo Planning (POMCP) is a powerful online algorithm that can generate online policies for large Partially Observable Markov Decision Processes. The lack of an explicit representation of the policy, however, hinders interpretability. In this work, we present a MAX-SMT based methodology to iteratively explore local properties of the policy. Our approach generates a compact and informative representation that describes the system under investigation.
POMDPs, POMCP, MAX-SMT, explainable planning, planning under uncertainty
File in questo prodotto:
File Dimensione Formato  
2021_AIRO2021_PolicyInterpretation(Mazzi).pdf

accesso aperto

Descrizione: Articolo principale
Tipologia: Versione dell'editore
Licenza: Dominio pubblico
Dimensione 474.13 kB
Formato Adobe PDF
474.13 kB Adobe PDF Visualizza/Apri

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/11562/1043020
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? ND
social impact