Explainable Multi-Agent Reinforcement Learning for Temporal Queries

Kayla Boggess, Sarit Kraus, Lu Feng

פרסום מחקרי: פרק בספר / בדוח / בכנספרסום בספר כנסביקורת עמיתים

תקציר

As multi-agent reinforcement learning (MARL) systems are increasingly deployed throughout society, it is imperative yet challenging for users to understand the emergent behaviors of MARL agents in complex environments. This work presents an approach for generating policy-level contrastive explanations for MARL to answer a temporal user query, which specifies a sequence of tasks completed by agents with possible cooperation. The proposed approach encodes the temporal query as a PCTL* logic formula and checks if the query is feasible under a given MARL policy via probabilistic model checking. Such explanations can help reconcile discrepancies between the actual and anticipated multi-agent behaviors. The proposed approach also generates correct and complete explanations to pinpoint reasons that make a user query infeasible. We have successfully applied the proposed approach to four benchmark MARL domains (up to 9 agents in one domain). Moreover, the results of a user study show that the generated explanations significantly improve user performance and satisfaction.

שפה מקוריתאנגלית
כותר פרסום המארחProceedings of the 32nd International Joint Conference on Artificial Intelligence, IJCAI 2023
עורכיםEdith Elkind
עמודים55-63
מספר עמודים9
מסת"ב (אלקטרוני)9781956792034
סטטוס פרסוםפורסם - 2023
אירוע32nd International Joint Conference on Artificial Intelligence, IJCAI 2023 - Macao, סין
משך הזמן: 19 אוג׳ 202325 אוג׳ 2023

סדרות פרסומים

שםIJCAI International Joint Conference on Artificial Intelligence
כרך2023-August

כנס

כנס32nd International Joint Conference on Artificial Intelligence, IJCAI 2023
מדינה/אזורסין
עירMacao
תקופה19/08/2325/08/23

ASJC Scopus subject areas

  • ???subjectarea.asjc.1700.1702???

טביעת אצבע

להלן מוצגים תחומי המחקר של הפרסום 'Explainable Multi-Agent Reinforcement Learning for Temporal Queries'. יחד הם יוצרים טביעת אצבע ייחודית.

פורמט ציטוט ביבליוגרפי