Explainability via Responsibility

Abstract

Procedural Content Generation via Machine Learning (PCGML) refers to a group of methods for creating game content (e.g. platformer levels, game maps, etc.) using machine learning models. PCGML approaches rely on black box models, which can be difficult to understand and debug by human designers who do not have expert knowledge about machine learning. This can be even more tricky in co-creative systems where human designers must interact with AI agents to generate game content. In this paper we present an approach to explainable artificial intelligence in which certain training instances are offered to human users as an explanation for the AI agent's actions during a co-creation process. We evaluate this approach by approximating its ability to provide human users with the explanations of AI agent's actions and helping them to more efficiently cooperate with the AI agent.

arXiv comment8 pages, 4 figures

References in corpus (7)

• Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model
• Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks
• Distilling Knowledge from Deep Networks with Applications to Healthcare Domain
• Super Mario as a String: Platformer Level Generation Via LSTMs
• Interpreting Deep Classifier by Visual Distillation of Dark Knowledge
• Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation
• Explainable AI: Deep Reinforcement Learning Agents for Residential Demand Side Cost Savings in Smart Grids