DESCRIPTION
Applications in the field of engineering often aim to simultaneously satisfy multiple criteria using a number of constraints or preferences. Many real-world environments also inherently have different objectives that can be aligned as well as conflicting, resulting in complex Pareto fronts. Moreover, in many cases the state of these systems changes over time, resulting in a dynamic environment for the learner. To efficiently explore these complex Parteo fronts, new exploration/exploitation techniques are needed.Inspiration for such techniques can be found in multi-objective optimization. The task of an optimization algorithm in a multi-criteria environment is either to learn a strategy that optimizes all criteria at the same time or to find a good compromise solution. Thus, learning in the multi-criteria framework can be considerable harder than in the standard single objective framework.
AIM AND SCOPE
The main goal of this special session is to help of unify and streamline research on learning in dynamic and uncertain multi-criteria environments. We want to bring together researchers from machine learning, optimization and artificial intelligence, interested multi-criteria decision making and/or multi-objective optimization in dynamic and uncertain environments. We also encourage submissions related to multi-criteria decision making and/or multi-objective optimization in other areas such as operation research, games and real-world applications.TOPICS OF INTEREST
Topics of interest include, but are not limited to:- Multi-objective reinforcement learning
- Multi-objective optimization algorithms (meta-heuristics, evolutionary algorithms, etc.) for dynamic and uncertain environments
- Theoretical results on the learnability in multi-objective dynamic and uncertain environments
- Novel algorithmic frameworks for multi-objective environments
- Multi-criteria aspects of robotics
- Multi-objective self-adapting systems
- Multi-objective automatic configuration systems
- Multi-objective games
- Multi-criteria decision making in dynamic and uncertain environments
- Real-world applications in engineering, business, computer science, biological sciences, scientific computation, etc. in Dynamic and Uncertain Environments
- Multi-criteria dynamic/reactive scheduling and planning
SUBMISSION
Authors are invited to submit their papers through the main IJCNN 2015 conference submission system at:http://ieee-cis.org/conferences/ijcnn2015/upload.php
Please make sure to select the Special Session under "S. SPECIAL SESSION TOPICS" in the "Main Research topic" drop-down list. Templates and detailed instructions for authors can be found at http://www.ijcnn.org/paper-submission
All papers submitted to the special session will be subject to the same peer-review procedure as regular papers. Accepted papers will be published in the conference proceedings.
ORGANIZERS
Madalina M. Drugan, Peter Vrancx, Ann NoweArtificial Intelligence Lab,
Vrije Universiteit Brussels, Belgium
{ Madalina.Drugan, pvrancx, Ann.Nowe }@vub.ac.be
https://ai.vub.ac.be/call_IJCNN2015
No comments:
Post a Comment
Note: only a member of this blog may post a comment.