Domain-Dependent Policy Learning using Neural Networks in Classical Planning
- Source: BSc thesis project at Foundations of Artificial Intelligence chair under supervision of Prof. Dr. Jörg Hoffmann
- Type: Individual work
- Language(s): Python and C++
In my BSc thesis I modified and implemented the neural network architecture of Action Schema Networks for application in classical deterministic planning and extensively evaluated the network’s suitability for this branch of automated planning.
For more details see my blog posts on this work available here.