Agents and Artificial Intelligence 12th International Conference, ICAART 2020, Valletta, Malta, February 22–24, 2020, Revised Selected Papers

This book contains the revised and extended versions of selected papers from the 12th International Conference on Agents and Artificial Intelligence, ICAART 2020, held in Valletta, Malta, in February 2020.

Overall, 45 full papers, 74 short papers, and 56 poster papers were carefully reviewed and selected from 276 initial submissions. 23 of the 45 full papers were selected to be included in this volume. These papers deal with topics such as agents and artificial intelligence.

Herd Behavior is Sufficient to Reproduce Human Evacuation Decisions During the Great East Japan Earthquake.- Intelligent Local Energy Communities: A Multiagent System Approach.- A Game-theoretical Incentive Mechanism for Local Energy Communities.- On the Combination of Game-Theoretic Learning and Multi Model Adaptive Filters.- Cooperative Multi-Agent Systems for the Multi-Target-Coverage Problem.- A Dynamic Scheduling Multiagent System for Truck Dispatching in Open-Pit Mines.- Time Matters: Exploring the Effects of Urgency and Reaction Speed in Automated Traders.- Cost-Sensitive Semi-Supervised Classification for Fraud Applications.- Blending NLP and Machine Learning for the Development of Winograd Schemas.- Cognitive Map Query Language for Temporal Domains.- Choose Your Words Wisely: Leveraging Embedded Dialog Trajectories to Enhance Performance in Open-Domain Conversations.- Heuristic Learning in Domain-independent Planning: Theoretical Analysis and Experimental Evaluation.- Knowledge Injection to Neural Networks with Progressive Learning Strategy.- A Scalable and Automated Machine Learning Framework to Support Risk Management.- Designing New Data Replication Strategies Automatically.- Trading Bias for Expressivity in Artificial Learning.- A Multi-Modal Audience Engagement Measurement System.- Learning Latent Variable Models with Discriminant Regularization.- Continuous Multi-Agent Path Finding via Satisfiability Modulo Theories.- Unsupervised Feature Value Selection Based on Explainability.- Reducing the Need for Manual Annotated Datasets in Aspect Sentiment Classification by Transfer Learning and Weak-Supervision.- Quantifying Gaze-Based Strategic Patterns in Physics Vector Field Divergence.- Economic and Food Safety: Optimized Inspection Routes Generation.