Explainable And Interpretable Reinforcement Learning For Robotics

Explainable and Interpretable Reinforcement Learning for Robotics

This book surveys the state of the art in explainable and interpretable reinforcement learning (RL) as relevant for robotics. While RL in general has grown in popularity and been applied to increasingly complex problems, several challenges have impeded the real-world adoption of RL algorithms for robotics and related areas. These include difficulties in preventing safety constraints from being violated and the issues faced by systems operators who desire explainable policies and actions. Robotics applications present a unique set of considerations and result in a number of opportunities related to their physical, real-world sensory input and interactions. The authors consider classification techniques used in past surveys and papers and attempt to unify terminology across the field. The book provides an in-depth exploration of 12 attributes that can be used to classify explainable/interpretable techniques. These include whether the RL method is model-agnostic or model-specific, self-explainable or post-hoc, as well as additional analysis of the attributes of scope, when-produced, format, knowledge limits, explanation accuracy, audience, predictability, legibility, readability, and reactivity. The book is organized around a discussion of these methods broken down into 42 categories and subcategories, where each category can be classified according to some of the attributes. The authors close by identifying gaps in the current research and highlighting areas for future investigation.

Machine Learning Under a Modern Optimization Lens

Explainable Agency in Artificial Intelligence

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