Events Calendar

MS Final Exam – Matthew L Olson

Counterfactual States for Atari Agents via Generative Deep Learning

Although deep reinforcement learning (RL) agents have produced impressive results in many domains, their decision making is difficult to explain to humans. To address this problem, past work has mainly focused on explaining why an action was chosen in a given state. A different type of explanation that is useful is a counterfactual, which deals with "what if?" scenarios. In this work, we introduce the concept of a counterfactual state to help humans gain a better understanding of what would need to change (minimally) in an Atari game image for the agent to choose a different action. Our contributions are twofold. First, we introduce a novel method to create counterfactual states from a generative deep learning architecture. Second, we evaluate the effectiveness of counterfactual states on human participants who are not machine learning experts. Our user study results suggest that our generated counterfactual states are useful in helping non-expert participants gain a better understanding of an agent's decision making process.

Major Advisor: Weng-Keen Wong
Committee: Alan Fern
Committee: Fuxin Li
Committee: Stefan Lee
GCR: Brett Tyler

Friday, November 8 at 11:00am to 1:00pm

Bexell Hall, 207
2251 SW Campus Way, Corvallis, OR 97331

Event Type

Lecture or Presentation

Event Topic

Research

Organization
Electrical Engineering and Computer Science
Contact Name

Calvin Hughes

Contact Email

calvin.hughes@oregonstate.edu

Subscribe
Google Calendar iCal Outlook

Recent Activity