---
title: "Extending Classical Planning to Real-World Execution with Machine Learning"
authors:
  - "Gerald DeJong"
  - "Scott Bennett"
doi: ""
url: "https://ijcai.org/proceedings/1995/149"
pdf: "https://ijcai.org/proceedings/1995/0149.pdf"
venue: "Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence"
year: 1995
pages: "1153-1160"
track: "Learning"
keywords:
---

# Extending Classical Planning to Real-World Execution with Machine Learning

Gerald DeJong, Scott Bennett

*Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence*, pages 1153-1160.

## Abstract

In previous work (Bennett 1993; DeJong and Bennett 1993) we proposed a machine learning approach called permissive planning to extend classical planning into the realm of real-world plan execution. Our prior results have been favorable but empirical (Bennett and DeJong 1991). Here we examine the analytic foundations of our empirical success. We advance a formal account of realworld planning adequacy. We prove that permissive planning does what it claims to do: it probabilistically achieves adequate real-world performance or guarantees that no adequate real-world planning behavior is possible within the flexibility allowed. We prove that the approach scales tractably. We prove that restrictions are necessary; without them permissive planning is impossible. We also show how these restrictions can be quite naturally met through schema-based planning and explanation-based learning.