Automated Rationale Generation: a Technique for Explainable AI and its Effects on Human Perceptions

{\em Automated rationale generation} is an approach for real-time explanation generation whereby a computational model learns to translate an autonomous agent's internal state and action data representations into natural language. Training on human explanation data can enable agents to learn to generate human-like explanations for their behavior. In this paper, using the context of an ] agent that plays {\em Frogger}, we describe (a) how to collect a corpus of explanations, (b) how to train a neural rationale generator to produce different styles of rationales, and (c) how people perceive these rationales. We conducted two user studies. The first study establishes the plausibility of each type of generated rationale and situates their user perceptions along the dimensions of \textit{confidence}, \textit{humanlike-ness}, \textit{adequate justification}, and \textit{understandability}. The second study further explores user preferences between the generated rationales with regard to \textit{confidence} in the autonomous agent, communicating \textit{failure} and \textit{unexpected behavior}. Overall, we find alignment between the intended differences in features of the generated rationales and the perceived differences by users. Moreover, context permitting, participants preferred detailed rationales to form a stable mental model of the agent's behavior.