This paper proposes and investigates a novel way of combining machine learning and heuristic search to improve domain independent planning. On the learning side, we use learning to predict the plan cost of a good solution for a given instance. On the planning side, we propose a bound-sensitive heuristic function that exploits such a prediction in a state-space planner. Our function combines the input prediction derived inductively) with some pieces of information gathered during search (derived deductively). As the prediction can sometimes be grossly inaccurate, the function also provides means to recognise when the provided information is actually misguiding the search. Our experimental analysis demonstrates the usefulness of the proposed approach in a standard heuristic best-first search schema.
|Title of host publication||Proceedings of the Thirtieth International Conference on Automated Planning and Scheduling|
|Subtitle of host publication||(ICAPS 2020)|
|Number of pages||5|
|Publication status||Published - 1 Jun 2020|
|Event||30th International Conference on Automated Planning and Scheduling - Nancy Congress Center – Centre Prouvé, Nancy, France|
Duration: 14 Jun 2020 → 19 Jun 2020
Conference number: 30
|Conference||30th International Conference on Automated Planning and Scheduling|
|Abbreviated title||ICAPS 2020|
|Period||14/06/20 → 19/06/20|
Percassi, F., Gerevini, A. E., Scala, E., Serina, I., & Vallati, M. (2020). Generating and Exploiting Cost Predictions in Heuristic State-Space Planning. In Proceedings of the Thirtieth International Conference on Automated Planning and Scheduling: (ICAPS 2020) (Vol. 30, pp. 569-573). AAAI press.