Section: Overall Objectives

Context and overall goal of the project

The overall goals of the project are to model, predict, understand, and control physical or artificial systems. The central claim is that Learning and Optimization approaches must be used, adapted and integrated in a seamless framework, in order to bridge the gap between the system under study on the one hand, and the expert's goal as to the ideal state/functionality of the system on the other hand.

Specifically, our research context is based on the following assumptions:

1. The systems under study range from large-scale engineering systems to physical or chemical phenomenons, including robotics and games. Such systems, sometimes referred to as complex systems, can hardly be modeled based on first principles due to their size, their heterogeneity and the incomplete information aspects involved in their behavior.

2. Such systems can be observed; indeed selecting the relevant observations and providing a reasonably appropriate description thereof are part of the problem to be solved. A further assumption is that these observations are sufficient to build a reasonably accurate model of the system under study.

3. The available expertise is sufficient to assess the system state, and any modification thereof, with respect to the desired states/functionalities. The assessment function is usually not a well-behaved function (differentiable, convex, defined on a continuous domain, etc.), barring the use of standard optimization approaches and making Evolutionary Computation a better suited alternative.

In this context, the objectives of TAO are threefold:

1. Investigating how specific prior knowledge and requirements can be accommodated in Machine Learning thanks to evolutionary computation (EC) and more generally Stochastic Optimization;

2. Investigating how statistical Machine Learning can be used to interpret, study and enhance evolutionary computation;

3. Facing diversified and real-world applications, requiring and suggesting new integrated ML/EC approaches.