Jasper van der Waa

J. van Diggelen, J. S. Barnhoorn, M. M. M. Peeters et al.

As intelligent systems are increasingly capable of performing their tasks without the need for continuous human input, direction, or supervision, new human-machine interaction concepts are needed. A promising approach to this end is human-agent teaming, which envisions a novel interaction form where humans and machines behave as equal team partners. This paper presents an overview of the current state of the art in human-agent teaming, including the analysis of human-agent teams on five dimensions; a framework describing important teaming functionalities; a technical architecture, called SAIL, supporting social human-agent teaming through the modular implementation of the human-agent teaming functionalities; a technical implementation of the architecture; and a proof-of-concept prototype created with the framework and architecture. We conclude this paper with a reflection on where we stand and a glance into the future showing the way forward.

Jasper van der Waa, Jurriaan van Diggelen, Karel van den Bosch et al.

Machine Learning models become increasingly proficient in complex tasks. However, even for experts in the field, it can be difficult to understand what the model learned. This hampers trust and acceptance, and it obstructs the possibility to correct the model. There is therefore a need for transparency of machine learning models. The development of transparent classification models has received much attention, but there are few developments for achieving transparent Reinforcement Learning (RL) models. In this study we propose a method that enables a RL agent to explain its behavior in terms of the expected consequences of state transitions and outcomes. First, we define a translation of states and actions to a description that is easier to understand for human users. Second, we developed a procedure that enables the agent to obtain the consequences of a single action, as well as its entire policy. The method calculates contrasts between the consequences of a policy derived from a user query, and of the learned policy of the agent. Third, a format for generating explanations was constructed. A pilot survey study was conducted to explore preferences of users for different explanation properties. Results indicate that human users tend to favor explanations about policy rather than about single actions.

Jasper van der Waa, Marcel Robeer, Jurriaan van Diggelen et al.

Recent advances in interpretable Machine Learning (iML) and eXplainable AI (XAI) construct explanations based on the importance of features in classification tasks. However, in a high-dimensional feature space this approach may become unfeasible without restraining the set of important features. We propose to utilize the human tendency to ask questions like "Why this output (the fact) instead of that output (the foil)?" to reduce the number of features to those that play a main role in the asked contrast. Our proposed method utilizes locally trained one-versus-all decision trees to identify the disjoint set of rules that causes the tree to classify data points as the foil and not as the fact. In this study we illustrate this approach on three benchmark classification tasks.