This book focuses on a subtopic of explainable AI (XAI) called explainable agency (EA), which involves producing records of decisions made during an agent's reasoning, summarizing its behavior in human-accessible terms, and providing answers to questions about specific choices and the reasons for them. We distinguish explainable agency from interpretable machine learning (IML), another branch of XAI that focuses on providing insight (typically, for an ML expert) concerning a learned model and its decisions. In contrast, explainable agency typically involves a broader set of AI-enabled techniques, systems, and stakeholders (e.g., end users), where the explanations provided by EA agents are best evaluated in the context of human subject studies.
The chapters of this book explore the concept of endowing intelligent agents with explainable agency, which is crucial for agents to be trusted by humans in critical domains such as finance, self-driving vehicles, and military operations. This book presents the work of researchers from a variety of perspectives and describes challenges, recent research results, lessons learned from applications, and recommendations for future research directions in EA. The historical perspectives of explainable agency and the importance of interactivity in explainable systems are also discussed. Ultimately, this book aims to contribute to the successful partnership between humans and AI systems.
Features:
Contributes to the topic of explainable artificial intelligence (XAI)
Focuses on the XAI subtopic of explainable agency
Includes an introductory chapter, a survey, and five other original contributions
Reihe
Sprache
Verlagsort
Verlagsgruppe
Zielgruppe
Für höhere Schule und Studium
Für Beruf und Forschung
Postgraduate and Professional
Illustrationen
31 s/w Abbildungen, 5 farbige Abbildungen, 4 s/w Photographien bzw. Rasterbilder, 3 Farbfotos bzw. farbige Rasterbilder, 27 s/w Zeichnungen, 2 farbige Zeichnungen, 18 s/w Tabellen
18 Tables, black and white; 2 Line drawings, color; 27 Line drawings, black and white; 3 Halftones, color; 4 Halftones, black and white; 5 Illustrations, color; 31 Illustrations, black and white
Maße
Höhe: 240 mm
Breite: 161 mm
Dicke: 14 mm
Gewicht
ISBN-13
978-1-032-40913-9 (9781032409139)
Copyright in bibliographic data and cover images is held by Nielsen Book Services Limited or by the publishers or by their respective licensors: all rights reserved.
Schweitzer Klassifikation
Dr. Silvia Tulli is an Assistant Professor at Sorbonne University. She received her Marie Curie ITN research fellowship and completed her Ph.D. at Instituto Superior Tecnico. Her research interests lie at the intersection of explainable AI, interactive machine learning, and reinforcement learning.
Dr. David W. Aha (UC Irvine, 1990) serves as the Director of the AI Center at the Naval Research Laboratory in Washington, DC. His research interests include goal reasoning agents, deliberative autonomy, case-based reasoning, explainable AI, machine learning (ML), reproducible studies, and related topics.
1. From Explainable to Justified Agency, 2. A Survey of Global Explanations in Reinforcement Learning, 3. Integrated Knowledge-Based Reasoning and Data-Driven Learning for Explainable Agency in Robotics, 4. Explanation as Question Answering Based on User Guides, 5. Interpretable Multi-Agent Reinforcement Learning with Decision-Tree Policies, 6. Towards the Automatic Synthesis of Interpretable Chess Tactics, 7. The Need for Empirical Evaluation of Explanation Quality
