| Abstract: | This article presents a view of planning as a task supported by a dynamic memory. This view attempts to ingegrate models of memory, learning, and planning into a single system that learns about planning by creating new plans and analyzing how they interact with the world. We call this view of planning case-based planning. A case-based planner makes use of its own past experience in developing new plans. It relies on its memory of observed effects, rather than a set of causal rules, to create and modify new plans. Memories of past successes are accessed and modified to create new plans. Memories of past failures are used to warn the planner of impending problems, and memories of past repairs are called upon to tell the planner how to deal with them. This view of planning from experience supports and is supported by a learning system that incorporates new experiences into the planner's episodic memory. This learning algorithm gains from the planner's failures as well as its successes. Successful plans are stored in memory, indexed by the goals they satisfy and the problems they avoid. Failures are also stored and indexed by the features in the world that predict them. By storing failures as well as successes, the planner is able to anticipate and avoid future plan failures. Case-based planning is aimed at improving planning behavior in three areas: failure avoidance, plan repair, and plan reuse. It also attempts gains over current learning systems, in that the learning is driven by the functional needs of a planner. |
