Mark T. Keane

Artificial intelligence (AI) systems increasingly make decisions that unfold over time: autonomous vehicles navigating traffic, robots executing manipulation sequences, game-playing agents taking moves toward their goals, and planning systems constructing multistep action sequences. Explaining such sequential behavior is fundamentally harder than explaining a single classification or regression output, yet this challenge has only recently received sustained research attention across the reinforcement learning, AI planning, robotics, and game-AI communities. This chapter provides an introduction to Explainable AI for Sequential Decision-Making (X-SDM). A unified taxonomy is developed that answers four core questions: what must be explained, who needs the explanation, how are explanations generated algorithmically, and how should they be evaluated. The taxonomy spans formal models including Markov Decision Processes and symbolic planning and covers the major families of explanation methods that have emerged across communities: contrastive and counterfactual explanations, feature importance and attribution methods, plan and goal explanations, model-reconciliation explanations, and intrinsically interpretable policies. These categories are illustrated with representative techniques, and a principled framework for user requirements grounded in situation-awareness theory is sketched. The chapter closes with ten open research questions that chart a roadmap for the field. The chapter integrates perspectives from reinforcement learning, AI planning, robotics, game AI, and cognitive science, offering students and researchers a structured entry point into this growing area.

In recent years, humanity has begun to experience the catastrophic effects of climate change as economic sectors (such as agriculture) struggle with unpredictable and extreme weather events. Artificial Intelligence (AI) should help us handle these climate challenges but its most promising solutions are not good at dealing with climate-disrupted data; specifically, machine learning methods that work from historical data-distributions, are not good at handling out-of-distribution, outlier events. In this paper, we propose a novel data augmentation method, that treats the predictive problems around climate change as being, in part, due to class-imbalance issues; that is, prediction from historical datasets is difficult because, by definition, they lack sufficient minority-class instances of “climate outlier events”. This novel data augmentation method -- called Counterfactual-Based SMOTE (CFA-SMOTE) -- combines an instance-based counterfactual method from Explainable AI (XAI) with the well-known class-imbalance method, SMOTE. CFA-SMOTE creates synthetic data-points representing outlier, climate-events that augment the dataset to improve predictive performance. We report comparative experiments using this CFA-SMOTE method, comparing it to benchmark counterfactual and class-imbalance methods under different conditions (i.e., class-imbalance ratios). The focal climate-change domain used relies on predicting grass growth on Irish dairy farms, during Europe-wide drought and forage crisis of 2018.

The use of Artificial Intelligence (AI) in high-risk, decision-making scenarios presents technical, safety, and normative challenges; problems that may only be ameliorated by human oversight. However, notions of human oversight lack a common foundational understanding: oversight architectures are not well defined, the roles involved remain unclear, and implementation steps are opaque. Hence, researchers and practitioners struggle to determine how to design, implement, and evaluate systems that enable effective human oversight. This paper advances a practical framework for effective human oversight of AI systems, based on a cross-disciplinary perspective that draws on insights from computer science, human-computer interaction, psychology, philosophy, and law. The core contributions are: (1) a foundational framework, with a working definition, architecture and processes for effective human oversight of AI systems; (2) an initial template for documenting oversight architectures and processes, applied to diverse domains; and (3) a synthesis of open research challenges that need to be considered in the emerging field of effective human oversight of AI systems.

Counterfactual explanations can promote accountability, fairness, and transparency in AI-supported decision-making by demonstrating how changes in input data can alter outcomes, offering actionable feedback for users to revise unfavorable decisions. However, the majority of counterfactual algorithms focus on tabular and image data, ignoring many high-stakes scenarios that rely on time series data. Furthermore, user studies of counterfactuals for time series are exceedingly rare. We address this research gap by proposing a novel methodology that advances carefully-controlled tests of counterfactual explanations for time series classification. In two experiments, participants were asked to classify time series plots and provide confidence ratings, before receiving feedback on the correct classification along with an explanation. The studies manipulated the explanation strategy used and the visualization used. Results indicate that counterfactual explanations elicit improved domain understanding and higher confidence in people in comparison to factual explanations. Wider implications for explanation in time series domains are discussed.

In recent years, humanity has begun to experience the catastrophic effects of climate change as economic sectors (such as agriculture) struggle with unpredictable and extreme weather events. Artificial Intelligence (AI) should help us handle these climate challenges but its most promising solutions are not good at dealing with climate-disrupted data; specifically, machine learning methods that work from historical data-distributions, are not good at handling out-of-distribution, outlier events. In this paper, we propose a novel data augmentation method, that treats the predictive problems around climate change as being, in part, due to class-imbalance issues; that is, prediction from historical datasets is difficult because, by definition, they lack sufficient minority-class instances of "climate outlier events". This novel data augmentation method -- called Counterfactual-Based SMOTE (CFA-SMOTE) -- combines an instance-based counterfactual method from Explainable AI (XAI) with the well-known class-imbalance method, SMOTE. CFA-SMOTE creates synthetic data-points representing outlier, climate-events that augment the dataset to improve predictive performance. We report comparative experiments using this CFA-SMOTE method, comparing it to benchmark counterfactual and class-imbalance methods under different conditions (i.e., class-imbalance ratios). The focal climate-change domain used relies on predicting grass growth on Irish dairy farms, during Europe-wide drought and forage crisis of 2018.