Description of the issue scope and motivation
Self-Learning Systems aim to achieve a goal -without being pre-programmed- in an environment that may be completely unknown initially. Self-learning algorithms are inspired by neuroscience and mimic he way the brain achieves cognition: they explore the environment following a try-and-error approach, or acquire knowledge from demonstrations provided by experts. The development of such a kind of systems is pushed forward by AI technologies such as Reinforcement Learning, Inverse Reinforcement Learning, and Learning by Demonstration. Their application spams from robotics and autonomous driving up to healthcare and precision medicine.
This special issue focuses on pattern recognition and their successive exploitation by Self-Learning Systems. The way Inverse Reinforcement Learning or Learning by Demonstration extract patterns from ‘demonstrated trajectories’, and how such patterns are successively exploited by a self-learning algorithm to optimize its policy or fasten its learning process, is of interest of this special issue.
Topics of interest
Inverse Reinforcement Learning
Learning-by-Demonstration and Imitation Learning
Pattern Recognition via Inverse Reinforcement Learning
Pattern Recognition from Demonstrations
Pattern exploitation in Self-Learning Systems
Pattern recognition in partially observable environments
Action-State trajectories analysis for pattern recognition and reward engineering
Pattern recognition and exploitation in Multi-Agent Self-Learning Systems
Pattern recognition and exploitation in Hierarchical Self-Learning Systems
Prospective authors should upload their submissions during the submission period through the Editorial Manager System(https://www.editorialmanager.com/PRLETTERS/default.aspx), with the article type selected as “SeLSPRE” All submissions should be prepared by adhering to the PRLetters guidelines by taking into account that VSI papers follow the same submission rules as regular articles. The submissions should be original and technically sound, and they should not have been published previously, nor be under consideration for publication elsewhere. If the submissions are extended works of previously published papers, the original works should be quoted in the References and a description of the changes that have been made should be provided. All templates for preparing the submissions are available on the journal web site (https://www.elsevier.com/journals/pattern-recognition-letters/0167-8655/guide-for-authors)
Submission Period: 1-20 October 2021
1st Round Review: 15 December 2021
Revised Submission: 31 January 2022
2nd Round Review (if required): 15 March 2022
Final submission: 15 April 2022
Final decision: 1 May 2022
Managing Guest Editor:
Antonio Coronato, CNR-ICAR (Italy)
Antonio Coronato is a researcher at the Institute of High-Performance Computing and Networking (ICAR) of the Italian National Research Council (CNR), Italy. His research focuses on Reinforcement Learning, Intelligent Environments and Intelligent Medical Software. He is head of the Research Group on Self-Learning and Self-Adaptive Systems at ICAR. He has served as general chair, program chair or member of the program committee of more than one hundred international conferences or workshops.
Giovanna Di Marzo Serugendo, University of Geneva, Switzerland
Giovanna Di Marzo Serugendo is full professor at the University of Geneva. Her current research interests are in the area of collective artificial intelligence systems, multi-agent systems and digital twins. She served in various functions, from General Chair, to PC chair to reviewers in more than 150 events. She founded the IEEE Conference on Self-adaptive and self-organising systems. She also served as EiC, guest editor and reviewer for several journals. She founded the ACM Transactions on adaptive autonomous systems.