In this paper we study the complexity of solving a problem when a solution of a similar instance is known. This problem is relevant whenever instances may change from time to time, and known solutions may not remain valid after the change. We consider two scenarios: in the first one, what is known is only a solution of the problem before the change; in the second case, we assume that some additional information, found during the search for this solution, is also known. In the first setting, the techniques from the theory of NP-completeness suffice to show complexity results. In the second case, negative results can only be proved using the techniques of compilability, and are often related to the size of considered changes.
[1]
Richard Fikes,et al.
STRIPS: A New Approach to the Application of Theorem Proving to Problem Solving
,
1971,
IJCAI.
[2]
Francesco M. Donini,et al.
Feasibility and Unfeasibility of Off-Line Processing
,
1996,
ISTCS.
[3]
Francesco M. Donini,et al.
Preprocessing of Intractable Problems
,
2002,
Inf. Comput..
[4]
Tom Bylander,et al.
Complexity Results for Planning
,
1991,
IJCAI.
[5]
Paolo Liberatore,et al.
On the Compilability of Diagnosis, Planning, Reasoning about Actions, Belief Revision, etc
,
1998,
KR.