Real-Time Scheduling with Independent Evaluators: Explainable Multi-Agent Approach

This study introduces a multi-agent reinforcement learning approach to address the challenges of real-time scheduling in dynamic environments, with a specific focus on healthcare operations. The proposed system integrates the Human-in-the-Loop (HITL) paradigm, providing continuous feedback from huma...

Full description

Saved in:
Bibliographic Details
Main Authors: Artem Isakov, Danil Peregorodiev, Ivan Tomilov, Chuyang Ye, Natalia Gusarova, Aleksandra Vatian, Alexander Boukhanovsky
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Technologies
Subjects:
Online Access:https://www.mdpi.com/2227-7080/12/12/259
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850238629834653696
author Artem Isakov
Danil Peregorodiev
Ivan Tomilov
Chuyang Ye
Natalia Gusarova
Aleksandra Vatian
Alexander Boukhanovsky
author_facet Artem Isakov
Danil Peregorodiev
Ivan Tomilov
Chuyang Ye
Natalia Gusarova
Aleksandra Vatian
Alexander Boukhanovsky
author_sort Artem Isakov
collection DOAJ
description This study introduces a multi-agent reinforcement learning approach to address the challenges of real-time scheduling in dynamic environments, with a specific focus on healthcare operations. The proposed system integrates the Human-in-the-Loop (HITL) paradigm, providing continuous feedback from human evaluators, and it employs a sophisticated reward function to attenuate the effects of human-driven events. Novel mapping between reinforcement learning (RL) concepts and the Belief–Desire–Intention (BDI) framework is developed to enhance the explainability of the agent’s decision-making. A system is designed to adapt to changes in patient conditions and preferences while minimizing disruptions to existing schedules. Experimental results show a notable decrease in patient waiting times compared to conventional methods while adhering to operator-induced constraints. This approach offers a robust, explainable, and adaptable solution for the challenging tasks of scheduling in the environments that require human-centered decision-making.
format Article
id doaj-art-f9a603eb0e4e4ed1bad7afe7cd2bc88a
institution OA Journals
issn 2227-7080
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Technologies
spelling doaj-art-f9a603eb0e4e4ed1bad7afe7cd2bc88a2025-08-20T02:01:24ZengMDPI AGTechnologies2227-70802024-12-01121225910.3390/technologies12120259Real-Time Scheduling with Independent Evaluators: Explainable Multi-Agent ApproachArtem Isakov0Danil Peregorodiev1Ivan Tomilov2Chuyang Ye3Natalia Gusarova4Aleksandra Vatian5Alexander Boukhanovsky6Department of Infocommunication Technologies, ITMO University, 197101 Saint Petersburg, RussiaDepartment of Infocommunication Technologies, ITMO University, 197101 Saint Petersburg, RussiaDepartment of Infocommunication Technologies, ITMO University, 197101 Saint Petersburg, RussiaSchool of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing 100081, ChinaDepartment of Infocommunication Technologies, ITMO University, 197101 Saint Petersburg, RussiaDepartment of Infocommunication Technologies, ITMO University, 197101 Saint Petersburg, RussiaDepartment of Infocommunication Technologies, ITMO University, 197101 Saint Petersburg, RussiaThis study introduces a multi-agent reinforcement learning approach to address the challenges of real-time scheduling in dynamic environments, with a specific focus on healthcare operations. The proposed system integrates the Human-in-the-Loop (HITL) paradigm, providing continuous feedback from human evaluators, and it employs a sophisticated reward function to attenuate the effects of human-driven events. Novel mapping between reinforcement learning (RL) concepts and the Belief–Desire–Intention (BDI) framework is developed to enhance the explainability of the agent’s decision-making. A system is designed to adapt to changes in patient conditions and preferences while minimizing disruptions to existing schedules. Experimental results show a notable decrease in patient waiting times compared to conventional methods while adhering to operator-induced constraints. This approach offers a robust, explainable, and adaptable solution for the challenging tasks of scheduling in the environments that require human-centered decision-making.https://www.mdpi.com/2227-7080/12/12/259decision makingexplainabilitymulti-agent systemsreal timereinforcement learningscheduling
spellingShingle Artem Isakov
Danil Peregorodiev
Ivan Tomilov
Chuyang Ye
Natalia Gusarova
Aleksandra Vatian
Alexander Boukhanovsky
Real-Time Scheduling with Independent Evaluators: Explainable Multi-Agent Approach
Technologies
decision making
explainability
multi-agent systems
real time
reinforcement learning
scheduling
title Real-Time Scheduling with Independent Evaluators: Explainable Multi-Agent Approach
title_full Real-Time Scheduling with Independent Evaluators: Explainable Multi-Agent Approach
title_fullStr Real-Time Scheduling with Independent Evaluators: Explainable Multi-Agent Approach
title_full_unstemmed Real-Time Scheduling with Independent Evaluators: Explainable Multi-Agent Approach
title_short Real-Time Scheduling with Independent Evaluators: Explainable Multi-Agent Approach
title_sort real time scheduling with independent evaluators explainable multi agent approach
topic decision making
explainability
multi-agent systems
real time
reinforcement learning
scheduling
url https://www.mdpi.com/2227-7080/12/12/259
work_keys_str_mv AT artemisakov realtimeschedulingwithindependentevaluatorsexplainablemultiagentapproach
AT danilperegorodiev realtimeschedulingwithindependentevaluatorsexplainablemultiagentapproach
AT ivantomilov realtimeschedulingwithindependentevaluatorsexplainablemultiagentapproach
AT chuyangye realtimeschedulingwithindependentevaluatorsexplainablemultiagentapproach
AT nataliagusarova realtimeschedulingwithindependentevaluatorsexplainablemultiagentapproach
AT aleksandravatian realtimeschedulingwithindependentevaluatorsexplainablemultiagentapproach
AT alexanderboukhanovsky realtimeschedulingwithindependentevaluatorsexplainablemultiagentapproach