Host institution: SCCH Duration 36 Months
Objectives: To develop deep reinforcement learning services that robustly predict, e.g., anomalies and trends in online and historic industrial processes as well as viable multi-scale spatio-temporal decision models for the distributed optimisation and control of such processes. These services will provide critical insights in cause-effect relationships between the product quality and production process sustainability / performance and the actually applied and virtually (agent-based) decisions on distributed process optimization and control paths under diverse process conditions and rages of uncertainty levels. The project team has experience in the derivation of agent-based (distributed) reinforcement learning techniques for optimization of real-time processes.
The candidate should have the following skills:
- a Master’s degree in computer science, artificial intelligence, mathematics or related field of study
- prior experience and background in machine learning, predictive modeling or reinforcement learning will be considered an advantage
- good skills in software development (preferably Python)
- ambitious in research and problem solving
- good communication skills, and motivation to work in a team
Expected Results:
Building a model for the optimal derivation of alternative process paths based on deep reinforcement learning models
Develop functions of optimization in graphs, with the objective of responding to the technical experts through the recommendation of prescriptive actions according to the search of the best probable scenario
Validate the knowledge acquired and the approaches devised on real case study applications
Publish 2 high impact journal articles and present innovative solutionsPlanned secondment(s): The PhD student is going to be seconded on M12 in TU Dublin for 12 months to work on LIVE LAB1 and 3 related case studies and in POLITO on M18 for 6 months to work on LIVE LAB 1 case study.
to access the application form click on this link: Application form