BSc Thesis III
Domain-Dependent Policy Learning using Neural Networks for Classical Planning (3/4) This third post about my undergraduate dissertation will cover my primary contributions to translate the architecture of Action Schema Networks, introduced in the previous post, for classical automated planning in the Fast-Downward framework.
The dissertation focuses on the application of ASNets in deterministic, classical planning. For this purpose, the network architecture was implemented and integrated into the Fast-Downward planning system [1] which is prominently used throughout classical planning research.