Supervisor synthesis of POMDP via automata learning

DOI10.1016/J.AUTOMATICA.2021.109654MaRDI QIDQ2665148zbMATH OpenOpenAlexFDO

Authors Bo Wu, Hai Lin, Xiao-Bin Zhang

Publication date 18 November 2021

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.automatica.2021.109654

zbMATH Keywords

automata learningformal methodspartially observable Markov decision processsupervisory control

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Synthesis problems (93B50)

Recommendations

• Task-aware verifiable RNN-based policies for partially observable Markov decision processes
• Enforcing almost-sure reachability in POMDPs
• Temporal logic motion planning using POMDPs with parity objectives
• DESPOT: online POMDP planning with regularization
• POMDP planning for robust robot control

Cites work

• Decision making under uncertainty. Theory and application. With contributions from Christopher Amato, Girish Chowdhary, Jonathan P. How, Hayley J. Davison Reynolds, Jason R. Thornton, Pedro A. Torres-Carrasquillo, N. Kemal Üre and John Vian
• Distributed Communication-Aware Motion Planning for Networked Mobile Robots Under Formal Specifications
• scientific article; zbMATH DE number 700091 (Why is no real title available?)
• scientific article; zbMATH DE number 781092 (Why is no real title available?)
• scientific article; zbMATH DE number 5585443 (Why is no real title available?)
• Learning regular sets from queries and counterexamples
• Permissive controller synthesis for probabilistic systems
• Permissive Supervisor Synthesis for Markov Decision Processes Through Learning
• Planning and acting in partially observable stochastic domains
• Randomness for free
• Synthesis of Joint Control and Active Sensing Strategies Under Temporal Logic Constraints
• Temporal logic motion planning for dynamic robots
• What is decidable about partially observable Markov decision processes with \(\omega\)-regular objectives

Cited in

(7)

• Maximum causal entropy specification inference from demonstrations
• Task-aware verifiable RNN-based policies for partially observable Markov decision processes
• Safety-aware apprenticeship learning
• Model Checking for Safe Navigation Among Humans
• A framework for transforming specifications in reinforcement learning
• Search and explore: symbiotic policy synthesis in POMDPs
• Offline supervisory control synthesis: taxonomy and recent developments

Describes a project that uses

Uses Software

• COMICS
• libalf

This page was built for publication: Supervisor synthesis of POMDP via automata learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2665148)