Markus Fritzsche — accepted AI-conference papers

2026

Managing Infinite Abstractions in Numeric Pattern Database Heuristics

Markus Fritzsche, Daniel Gnad, Mikhail Gruntov, Alexander Shleyfman

AAAI 2026technical

Pattern Database (PDB) heuristics are an established approach in optimal classical planning that is used in state-of-the-art planning systems. PDBs are based on projections, which induce an abstraction of the original problem. Computing all cheapest plans in the abstraction yields an admissible heur

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

Symmetry-Aware Transformer Training for Automated Planning

Markus Fritzsche, Elliot Gestrin, Jendrik Seipp

AAAI 2026technical

While transformers excel in many settings, their application in the field of automated planning is limited. Prior work like PlanGPT, a state-of-the-art decoder-only transformer, struggles with extrapolation from easy to hard planning problems. This in turn stems from problem symmetries: planning tas

Cited by 0 Source ↗PDF ↗Scholar ↗