Learning while searching in symbolic planners

About this position

Pictus PhD Fellowship Programme

Czech Technical University in Prague – International PhD Programme (PICTUS) will recruit 8 students (see Eligibility criteria below) for a full 48-month employment contract and enroll them in a specific PhD course. Candidates should prepare their own research proposal from the List of topics for the 2nd Call .

Application form should be filled and all required documents uploaded using the dedicated electronic form.

helpdesk: pictus@cvut.cz

Guide for Applicants

Learning while searching in symbolic planners

Description:

The symbolic search in large state spaces is one of the foundational problems in AI. The modern solvers typically use some variant of tree search algorithm with a strong heuristic function. Not surprisingly, the heuristic function is nowadays frequently realized by neural networks.

The problem is that the training set usually contains small problem instances in few numbers while the testing set contains large instances, which inevitably lead to issues with generalization. This project will therefore investigate options, how to adapt the heuristic function during the search to efficiently use information from states visited during the search. We believe this would make the search more similar to humans, which also adapts their behavior with respect to their immediate experience.

We anticipate two issues: computational complexity and construction of the feedback signal from explored state space. The ultimate goal is to make the planning system competitive to (read ultimately much better than) to state of the art planners based on heuristics created by humans.

Secondment:

Artificial Intelligence and Integrated Computer Systems, Linköping University,

Co-supervisor: prof. Jendrik Seipp