Search Results for author: Argaman Mordoch

Found 2 papers, 0 papers with code

Safe Learning of PDDL Domains with Conditional Effects -- Extended Version

no code implementations22 Mar 2024 Argaman Mordoch, Enrico Scala, Roni Stern, Brendan Juba

We prove that learning non-trivial safe action models with conditional effects may require an exponential number of samples.

Enhancing Numeric-SAM for Learning with Few Observations

no code implementations17 Dec 2023 Argaman Mordoch, Shahaf S. Shperberg, Roni Stern, Berndan Juba

It runs in polynomial time and is guaranteed to output an action model that is safe, in the sense that plans generated by it are applicable and will achieve their intended goals.

Cannot find the paper you are looking for? You can Submit a new open access paper.