Loading...
Please wait, while we are loading the content...
Similar Documents
Learned rewrite rules versus learned search control rules to improveplan qualityMuhammad
| Content Provider | Semantic Scholar |
|---|---|
| Author | Upal, Afzal René |
| Copyright Year | 1999 |
| Abstract | Domain independent planners can produce better-quality plans through the use of domain-dependent knowledge , typically encoded as search control rules. The planning-by-rewriting approach has been proposed as an alternative technique for improving plan quality. We present a system called Sys-REWRITE that automatically learns plan rewriting rules and compare it with Sys-SEARCH-CONTROL, a system that automatically learns search control rules for partial order planners. Our results support the usefulness of planning by rewriting approach to eeciently generate high quality plans and demonstrate a way of automatically learning these rules from analyzing partial-order planning episodes. Our empirical comparison of the two systems suggests that while Sys-REWRITE can quickly learn to produce higher quality plans than Sys-SEARCH-CONTROL, Sys-SEARCH-CONTROL is more eecient than Sys-REWRITE. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://www.cs.ualberta.ca/~upal/plan/5/5.ps |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
