Search Results for author:
Found 4 papers, 1 papers with code
Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning
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.
Counterfactual States for Atari Agents via Generative Deep Learning
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.
Counterfactual Regularization for Model-Based Reinforcement Learning
In sequential tasks, planning-based agents have a number of advantages over model-free agents, including sample efficiency and interpretability.
Open Set Learning with Counterfactual Images
In open set recognition, a classifier must label instances of known classes while detecting instances of unknown classes not encountered during training.
