Machine learning methods and algorithms for sequential decision-making problems in the presence[...]

European Commission; Italia; In loco; EUR 30.000 - 50.000; Tempo pieno

Descrizione del lavoro

The European Commission is seeking a full-time researcher in Italy to develop methods in machine learning focusing on human feedback interaction. The role involves defining learning frameworks, analyzing theoretical properties, and experimental validations aligned with the National Recovery and Resilience Plan.

Competenze

• Recognised Researcher or higher level profile.
• Experience in machine learning research required.
• Familiarity with theoretical properties of learning algorithms preferred.

Mansioni

• Develop methods and algorithms for machine learning.
• Analyze theoretical properties of learning problems.
• Conduct experimental validation in simulation.

Conoscenze

Machine Learning

Algorithm Development

Imitation Learning

Reinforcement Learning

Online Learning

Formazione

PhD in Computer Science or related field

Descrizione del lavoro

Organisation/Company Politecnico di Milano Research Field Computer science Researcher Profile Recognised Researcher (R2) Leading Researcher (R4) First Stage Researcher (R1) Established Researcher (R3) Country Italy Application Deadline 31 Jul 2025 - 23:59 (UTC) Type of Contract Temporary Job Status Full-time Hours Per Week 00 Offer Starting Date 1 Jan 1970 Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Is the Job related to staff position within a Research Infrastructure? No

Offer Description

The research activity will focus on the development of methods and algorithms for machine learning that enable artificial agents to acquire skills through interaction (feedback) with humans. The objectives include: the definition of a framework for studying learning problems involving human feedback; the analysis of the theoretical properties (statistical and/or computational) of the related learning problems; the development of learning algorithms; the study of their theoretical properties (statistical and/or computational); and, possibly, experimental validation in simulation. The research will leverage techniques from imitation learning, reinforcement learning, and/or online learning. All activities are fully aligned with the general principles of the National Recovery and Resilience Plan (PNRR) 'Missione 4: Istruzione e Ricerca' and the extended PNRR partnership 'Future of Artificial Intelligence Research.'