DC2 FINALITY: Delayed Reinforcement Learning with Teams and Games

University of Avignon; France; Sur place; EUR 40 000 - 60 000; Plein temps

Résumé du poste

A leading research institution in France is offering a PhD position focused on applied mathematics within the framework of an EU Doctoral Network. The candidate will conduct research on distributed systems and collaborate with international partners. A strong background in mathematical modeling and performance evaluation is essential, along with excellent communication skills. The role offers competitive salary, full social security coverage, and opportunities for professional development.

Prestations

Competitive Salary

Social Security & Pension Coverage

Mobility Allowance

Professional Development Opportunities

Qualifications

• Master's degree (or equivalent) in Applied Mathematics or Theoretical Computer Science.
• Strong background in modeling and performance evaluation.
• Interest and skills in computer programming are a plus.

Responsabilités

• Explore trade-offs between distribution of policies in a distributed system.
• Maintain consistency among agents with imperfect information.
• Collaborate with international research partners and contribute to the FINALITY project.

Description du poste

Organisation/Company University of Avignon Department CERI Research Field Mathematics » Applied mathematics Researcher Profile First Stage Researcher (R1) Positions PhD Positions Country France Application Deadline 31 Jan 2026 - 23:59 (Europe/Paris) Type of Contract Temporary Job Status Full-time Hours Per Week 36 Offer Starting Date 1 Nov 2025 Is the job funded through the EU Research Framework Programme? Horizon Europe - MSCA Marie Curie Grant Agreement Number 101168816 Is the Job related to staff position within a Research Infrastructure? No

Offer Description

The Laboratory of Informatics of the University of Avignon (LIA), Avignon, France, offers a PhD position for a Doctoral Candidate (DC) in the framework of the MSCA Doctoral Network FINALITY (saFe learnINg for LArge scaLe InTerconnected sYstems).

The presence of delays for agents implementing a policy in a distributed system requires specific tools for the convergence and the adjustment of policies. This thesis will explore the tradeoffs between and distribution of policies among different agents and problems related to the presence of material constraints, e.g., the delays or partial information shared among the orchestrators performing RA. Maintaining consistency in a team of orchestrators in presence of imperfect information shared by individual orchestrators is a skill which requires specific skill development.

Secondments: this project is carried out in tight collaboration with associated industrial groups, and visits to their laboratories are expected during the project. SAFRAN Passenger Innovations, Germany, for application to fleets of airborne communication systems, KTH, Sweden, for RL in competitive scenarios, TU DELFT, the Netherlands, for allocation of resources by teams of edge orchestrators. Willingness to travel and spend time abroad is essential.

Context: The FINALITY DN advances the theoretical computer science curriculum focusing on the mastery of prompt and safe learning techniques for interconnected systems. The 15 FINALITY trainees will develop and integrate innovative methodological tools specialized for AI-based resource allocation, particularly in the context of large-scale critical infrastructures for communication and computing. They will develop and validate AI methods that are safe by respecting system boundaries and are prompt in adapting to the environmental changes. Throughout their research training, the FINALITY candidates will prioritize the principles of fairness and computational parsimony of AI methods.

VERY IMPORTANT: please check MSCA Doctoral Networks Eligibility Criteria; in particular, residence in France for more than 12 months in the past 36 months before hiring leads to automatic rejection.

• a master's degree (or equivalent) in a relevant field such as Applied Mathematics or Theoretical Computer Science
• the ideal profile is an applied mathematician willing to perform computer science applications
• curriculums with low marks in basic mathematical fields will not be considered

Strong background in:

• modeling and performance evaluation.
• tools including but not limited to: control theory, game theory, stochastic processes, Markov theory and machine learning (especially Reinforcement learning, Bayesian Optimization and Neural Networks).
• an interest and skills in computer programming would be an asset for numerical analysis via, e.g., simulation tools.
• technological competences in computing and telecommunications are welcome but not mandatory.

Interdisciplinary Research:

• Ability to work in an interdisciplinary research environment, bridging the fields of mathematics, engineering, ICT and informatics.

Communication Skills:

• Excellent written and verbal communication skills, with the ability to present research findings effectively.

Collaboration and Teamwork:

• Ability to collaborate with research groups during secondments to external institutions.
• Willingness to acquire and propose new methodologies and techniques, especially during secondments to industry and different academic partners.

Motivation and Initiative:

• Intrinsic motivation to contribute to the objectives of the FINALITY project and the ability to take initiative in research activities.

Ability to Contribute to Project Goals:

• Enthusiasm for contributing to the overall goals of the FINALITY project.
• This project is carried out in strong collaboration with international groups, and visits to their laboratories are expected during the project. A willingness to travel and spend working time outside the LIA laboratory is therefore essential.

Languages ENGLISH Level Excellent

Additional Information

The recruited researcher will be part of the FINALITY doctoral programme. FINALITY offers a thorough scientific education in the frame of a doctoral training programme and the possibility to participate in specific international training courses, workshops and conferences. The team of doctoral candidates will participate in a European research project with high international visibility. They will have the possibility to perform research visits to internationally renowned research labs in Europe under a prestigious MSCA Fellowship.

Practical benefits include:

• Competitive Salary: The gross monthly salary is € 3224 €, subject to tax and social security deductions.
• Social Security & Pension: Full coverage under French’s social security and pension schemes.
• Mobility Allowance: Additional monthly allowance for living costs related to relocation.
• Other Allowances: Family allowance, long-term leave allowance, and special needs allowance will be available if needed.
• Professional Development: Access to high-quality training, networking opportunities, and career development support.

Eligibility criteria

Candidates must fulfil the mandatory MSCA Doctoral Networks Eligibility Criteria:

• Mobility rule: Researchers must not have resided or carried out their main activity (e.g., work, study) in the country of the host organisation for more than 12 months in the 3 years immediately before the recruitment date (i.e., start of employment).
• PhD rule: Applicants must be doctoral candidates, i.e., must not already be in possession of a doctoral degree at the date of recruitment.

Failure to comply to MSCA Doctoral Networks Eligibility Criteria will lead to automatic rejection.

Applicants of all nationalities are welcome to apply.

Selection process

To apply, please complete the following 2 steps:

Optional step 2) signal your interest by sending your CV, covering letter, academic marks for both undergraduate and graduate studies, and recommendation letters in a single pdf document to Francesco De Pellegrini: [e-mail]

We will adopt the principles of the European Charter for Researchers and Code of Conduct for the Recruitment of Researchers, promoting open, merit-based and transparent recruitment and attractive working and employment conditions.

The main supervisor will make a pre-selection of eligible candidates for the open position. Ineligible and incomplete applications will not be considered.

The pre-selected candidates will be invited to an online interview with at least one additional member of the DC supervisory team and in coordination with the FINALITY Supervisory Board.

A reserve list of candidates may be kept for up to 6 months