arXiv (Cornell University) · 2019 · 17 citations · 13 references
ComputingAutonomous SystemsComputer ScienceArtificial IntelligenceKnowledge RepresentationMachine LearningCounterfactual ReasoningDeep LearningExplainable Machine LearningGenerative ModelingNeural NetworksReinforcement LearningAutomated Machine LearningDeep Reinforcement LearningUser Study Evaluation
Although deep reinforcement learning 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. We introduce a novel method to create counterfactual states from a generative deep learning architecture. In addition, 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.
13
Human-level control through deep reinforcement learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver et al. · Nature · 2015 · 30K citations
Marco Túlio Ribeiro, Sameer Singh, Carlos Guestrin · 2016 · 15.2K citations
Automatic differentiation in PyTorch
Adam Paszke, Sam Gross, Soumith Chintala et al. · 2017 · 11.1K citations