Mental Models of Mere Mortals with Explanations of Reinforcement Learning
Abstract
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 as follows: (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.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- May 30, 2020
- Source ID
- 10.1145/3366485
Entities
People
- Alan Fern
- Amrita Sadarangani
- Andrew Anderson
- Evan Newman
- Jed Irvine
- Jonathan Dodge
- Margaret M. Burnett
- Matthew Olson
- Souti Chattopadhyay
- Zoe Juozapaitis
Organizations
- Defense Advanced Research Projects Agency
- Oregon State University