Doctoral and Postdoctoral Openings Representation Learning for Planning
We have several funded slots for doctoral students and postdoctoral researchers at the AI and ML group at the Universitat Pompeu Fabra, Barcelona, Spain to carry out research on Representation Learning for Planning.
The project addresses a research problem that is at the heart of the current split in AI between data-based learners and model-based reasoners: the problem of learning symbolic representations from raw perceptions.
In our case, first order symbolic representations, involving objects and relations, are to be learned from scratch for planning and generalized planning. Other dimensions of representation learning to be pursued in the project include representation grounding, transfer, composition, and scaffolding.
We are seeking highly motivated doctoral students and postdoctoral researchers eager to make a difference in these problems, with experience in areas such as machine learning, planning, logic and knowledge representation, combinatorial optimization and SAT.
Ideal candidates should be able to do or learn to do theoretical and experimental work, logic and algorithms, and programming and “differential programming” (deep learning). Good oral and written skills in English are required.
The funds come from an Advanced ERC Grant (RLeap: From Data-based to Model-based AI: Representation Learning for Planning), the EU funded TAILOR network (Trustworthy AI: Integrating Learning, Optimization and Reasoning), and a grant from the Wallenberg (KAW) Foundation and Swedish WASP program in AI.
The deadline for PhD students is July 10th. For Postdocs, there is no deadline and the search for qualified candidates will continue until the slots are filled.
Interested PhD candidates should send a CV, transcripts, three reference letters, and a motivation statement to: rleap.artint@gmail.com. Postdocs should send a CV, contact details of three references, and a research statement.
We are flexible to alleviate effects of COVID-19, with the possibility of working remotely while needed, once the working documents are ready.
