Learning How to Search for Plans with Exponentially Less Space
Quick summary
arXiv:2610.10954v1 Announce Type: new Abstract: Heuristic search for a plan can store exponentially many states, even when its heuristic is almost perfect. We instead learn search control, one specification per domain, written as an indexical policy: a generalized policy with registers that hold objects and modes that sequence its rules. We add the choose rule, which loads an object into a register and marks a backtracking point, where one candidate suffices; every other rule must work for all of its outcomes and needs no search. Our main result is that structural termination, which rules out
Key takeaways
- arXiv:2610.10954v1 Announce Type: new Abstract: Heuristic search for a plan can store exponentially many states, even when its heuristic is almost perfect.
- We instead learn search control, one specification per domain, written as an indexical policy: a generalized policy with registers that hold objects and modes that sequence its rules.
- We add the choose rule, which loads an object into a register and marks a backtracking point, where one candidate suffices; every other rule must work for all of its outcomes and needs no search.
Why it matters
The significance is not only the legal text but how it changes product design. Decisions around “Learning How to Search for Plans with Exponentially Less Space” may reshape data collection, model training, output accountability and market access.
Member comments