Explainable Multi-Agent Reinforcement Learning for Temporal Queries

Kayla Boggess, Sarit Kraus, Lu Feng

نتاج البحث: فصل من :كتاب / تقرير / مؤتمرمنشور من مؤتمرمراجعة النظراء

ملخص

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.

اللغة الأصليةالإنجليزيّة
عنوان منشور المضيفProceedings of the 32nd International Joint Conference on Artificial Intelligence, IJCAI 2023
المحررونEdith Elkind
الصفحات55-63
عدد الصفحات9
رقم المعيار الدولي للكتب (الإلكتروني)9781956792034
حالة النشرنُشِر - 2023
الحدث32nd International Joint Conference on Artificial Intelligence, IJCAI 2023 - Macao, الصين
المدة: ١٩ أغسطس ٢٠٢٣٢٥ أغسطس ٢٠٢٣

سلسلة المنشورات

الاسمIJCAI International Joint Conference on Artificial Intelligence
مستوى الصوت2023-August

!!Conference

!!Conference32nd International Joint Conference on Artificial Intelligence, IJCAI 2023
الدولة/الإقليمالصين
المدينةMacao
المدة١٩/٠٨/٢٣٢٥/٠٨/٢٣

All Science Journal Classification (ASJC) codes

  • !!Artificial Intelligence

بصمة

أدرس بدقة موضوعات البحث “Explainable Multi-Agent Reinforcement Learning for Temporal Queries'. فهما يشكلان معًا بصمة فريدة.

قم بذكر هذا