Local and global explanations of agent behavior: Integrating strategy summaries with saliency maps
Authors:
- Tobias HuberTHTobias Huber
- Katharina WeitzKWKatharina Weitz
- Elisabeth AndréEAElisabeth André
- Ofra AmirOAOfra Amir
Open Access
- 1 December 2021
- journal article
- research article
- Published by Elsevier in Artificial Intelligence
- Vol. 301
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- Deutsche Forschungsgemeinschaft
- Israel Science Foundation (2185/20)
This publication has 19 references indexed in Scilit:
- Explanation in artificial intelligence: Insights from the social sciencesArtificial Intelligence, 2019
- Guidelines for reinforcement learning in healthcareNature Medicine, 2019
- CNN Fixations: An Unraveling Approach to Visualize the Discriminative Image RegionsIEEE Transactions on Image Processing, 2018
- Methods for interpreting and understanding deep neural networksDigital Signal Processing, 2018
- On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance PropagationPLOS ONE, 2015
- Human-level control through deep reinforcement learningNature, 2015
- The Arcade Learning Environment: An Evaluation Platform for General AgentsJournal of Artificial Intelligence Research, 2013
- Three Approaches to Qualitative Content AnalysisQualitative Health Research, 2005
- Trust in Automation: Designing for Appropriate RelianceHuman Factors: The Journal of the Human Factors and Ergonomics Society, 2004
- XPLAIN: a system for creating and explaining expert consulting programsArtificial Intelligence, 1983