Graduate Thesis Or Dissertation


Mental Models of Mere Mortals with Explanations of Reinforcement Learning Público Deposited

Conteúdo disponível para baixar

Baixar PDF


Attribute Name LabelAttribute Values Label
  • How should reinforcement learning (RL) agents explain themselves to humans not trained in AI? To gain insights into this question, we conducted a 124 participant, four-treatment experiment to compare participants’ mental models of an RL agent in the context of a simple Real-Time Strategy (RTS) game. The four treatments isolated two types of explanations vs. neither vs. both together. The two types of explanations were: (1) saliency maps (an “Input Intelligibility Type” that explains the AI’s focus of attention), and (2) reward-decomposition bars (an “Output Intelligibility Type” that explains the AI’s predictions of future types of rewards). Our results show that a combined explanation that included saliency and reward bars was needed to achieve a statistically significant difference in participants’ mental model scores over the no-explanation treatment. However, this combined explanation was far from a panacea: it exacted disproportionately high cognitive loads from the participants who received the combined explanation. Further, in some situations, participants who saw both explanations predicted the agent’s next action worse than all other treatments’ participants.
License Label
Resource Type
Date issued
Degree Level
Degree Name
Degree Field
Degree Grantors
Graduation Year
Contributor Advisor
Contributor Committeemember
Academic Affiliation
Declaração de direitos


Relationships Parent Rows Label

Rows Empty Text

Em Collection: