Case - Based Planning : A Framework for Planning from Experience KRISTIAN

This article presents a view of planning as o task supported by o dynamic memory. This view attempts to ingegrote 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 ond modify new plans. Memories of past successes are accessed and modified to create new plans. Memories of past failures ore used to worn the planner of impending problems, and memories of past repairs are called upon to tell the planner how to deol with them. This view of plonning from experience supports and is supported by a learning system that incorporates new experiences into the planner’s episodic memory. This leorning algorithm gains from the planner’s failures as well as its successes. Successful plans are stored in memory, indexed by the goals they satisfy ond 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 anticipofe and avoid future plan failures. Case-based planning is aimed at improving planning behovior in three oreas: foilure avoidance, plan repair, and plan reuse. It also attempts gains over current learning systems, in thot the learning is driven by the functional needs of 0 planner.