Agents and Artificial Intelligence [electronic resource] : 14th International Conference, ICAART 2022, Virtual Event, February 3–5, 2022, Revised Selected Papers /

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.

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 3–5, 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.