2 code implementations • 29 Jan 2021 • Matthew L. Olson, Roli Khanna, Lawrence Neal, Fuxin Li, Weng-Keen Wong
Our second user study investigates if counterfactual state explanations can help non-expert participants identify a flawed agent; we compare against a baseline approach based on a nearest neighbor explanation which uses images from the actual game.
no code implementations • 27 Sep 2019 • Matthew L. Olson, Lawrence Neal, Fuxin Li, Weng-Keen Wong
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.
no code implementations • 25 Sep 2019 • Lawrence Neal, Li Fuxin, Xiaoli Fern
In sequential tasks, planning-based agents have a number of advantages over model-free agents, including sample efficiency and interpretability.
no code implementations • ECCV 2018 • Lawrence Neal, Matthew Olson, Xiaoli Fern, Weng-Keen Wong, Fuxin Li
In open set recognition, a classifier must label instances of known classes while detecting instances of unknown classes not encountered during training.