ACI Journal Articles


Toward a Psychology of Deep Reinforcement Learning Agents Using a Cognitive Architecture

Document Type


USMA Research Unit Affiliation

Army Cyber Institute

Publication Date



We argue that cognitive models can provide a common ground between human users and deep reinforcement learning (Deep RL) algorithms for purposes of explainable artificial intelligence (AI). Casting both the human and learner as cognitive models provides common mechanisms to compare and understand their underlying decision-making processes. This common grounding allows us to identify divergences and explain the learner’s behavior in human understandable terms. We present novel salience techniques that highlight the most relevant features in each model’s decision-making, as well as examples of this technique in common training environments such as Starcraft II and an OpenAI gridworld.

Peer Reviewed


Record links to items hosted by external providers may require fee for full-text.