The Inria Lille - Nord Europe Research Center was founded in 2008 and employs a staff of 360, including 300 scientists working in sixteen research teams. Recognised for its outstanding contribution to the socio-economic development of the Hauts-De-France région, the Inria Lille - Nord Europe Research Center undertakes research in the field of computer science in collaboration with a range of academic, institutional and industrial partners.

 The strategy of the Center is to develop an internationally renowned centre of excellence with a significant impact on the City of Lille and its surrounding area. It works to achieve this by pursuing a range of ambitious research projects in such fields of computer science as the intelligence of data and adaptive software systems. Building on the synergies between research and industry, Inria is a major contributor to skills and technology transfer in the field of computer science.

Project CausalXRL is a publicly funded collaborative project research problem. CausalXRL is gathering the dpt. of computer science of U. Sheffield, the faculty of computer science of U. Vienna, and Inria/Scool team.

The recruitee will be based in Scool group, in Villeneuve d'Ascq in France. As part of the project, he will regularly travel and meet people in Sheffiled and Vienna. He will also participate to scientific events, such as scientific conferences.

Reinforcement learning is today a well developed field of research, enjoying significant applications. Its most well-known applications are related to learning to play games and become expert in playing Backgammon (1994), Atari video-games (2013), and go and other board games (2017). However spectacular, RL successes have been obtained in applications in which a the environent may be simulated, and the agent may be trained over billions of trials, sometimes over months, on large scale computing infrastructures for the most recent ones. When one departs from these comfortable applications, RL faces many challenges. Among others, RL faces the challenge also faced by other deep learning applications, that of being able to explain what it does, or to provide human beings with information about what it does and how it achieves its prediction. This is the well-known "explanability" challenge. In the CausalXRL project, we wish to investigate the use of causality to let an RL be able to explain what it does, or let human beings understand how and why it performs.

The recruitee will collaborate with the project partner groups for the purpose of making scientific progress in the field of causal explanable reinforcement learning, fundamental research and its application.

The recruitee will perform standard research activities, involving reading scientific publications, proposing new ideas related to the project, argueing, developing them, presenting them informally to partners, and also through seminars and research group meetings, writing scientific publications and submit them to top conference and journals of the field.

Technical skills and level required: proficiency in python, pytorch, machine learning packages. Skills in C/C++ will also be appreciated.

Everything will be implemented in Linux/Ubuntu, in an open source software state of mind.

Abiity to work, interact, and collaborate with other researchers (in English)

• Subsidized meals
• Partial reimbursement of public transport costs
• Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
• Possibility of teleworking (after 6 months of employment) and flexible organization of working hours
• Professional equipment available (videoconferencing, loan of computer equipment, etc.)
• Social, cultural and sports events and activities
• Access to vocational training
• Social security coverage

Depending on profile and experience, between 35 k€ and 43 k€ gross per year