This book contains the revised and extended versions of selected papers from the 14th International Conference on Agents and Artificial Intelligence, ICAART 2022, which took place virtually during February 35, 2022. The conference was originally planned to take place in Vienna, Austria, but had to change to an online format due to the COVID-19 pandemic.
The 9 full papers included in this book were carefully reviewed and selected from 302 submissions. They were organized in topical sections as follows: agents; artificial intelligence.
Agents.- Efficient Visual Sign Assignment for Crowd Evacuation
Guidance Considering Risks and Multiple Objectives.- Negotiation Protocol
with Learned Handover of Important Tasks for Planned Suspensions in
Multi-Agent Patrol Problems.- Artificial Intelligence.- Comparing Beta-VAE to
WGAN-GP for Time Series Augmentation to Improve Classification
Performance.- Safe Policy Improvement Approaches and Their
Limitations.- Integrative System of Deep Classifiers Certification: Case
of Convolutional Attacks.- Co-operative Multi-agent Twin Delayed DDPG for
Robust Phase Duration Optimization of Large Road Networks.- Generating the
Gopher's Grounds: Form, Function, Order, and Alignment.- Domain Dependent
Parameter Setting in SAT Solver using Machine Learning Techniques.- More
Sustainable Text Classification via Uncertainty Sampling and
a Human-in-the-Loop.
