On AO*, Proof Number Search and Minimax Search

TL;DR

This paper explores the relationships between AO*, proof number search, and minimax search, highlighting how these algorithms interconnect within AND/OR graph models and proposing potential extensions for improved search strategies.

Contribution

It clarifies the connections among these search algorithms and suggests that proof number search can serve as a more informed alternative to AO* for general AND/OR graphs.

Findings

Proof number search can replace AO* in solving AND/OR graphs.

Minimax search principles can be extended with dual heuristics.

The algorithms are interconnected through their underlying graph models.

Abstract

We discuss the interconnections between AO*, adversarial game-searching algorithms, e.g., proof number search and minimax search. The former was developed in the context of a general AND/OR graph model, while the latter were mostly presented in game-trees which are sometimes modeled using AND/OR trees. It is thus worth investigating to what extent these algorithms are related and how they are connected. In this paper, we explicate the interconnections between these search paradigms. We argue that generalized proof number search might be regarded as a more informed replacement of AO* for solving arbitrary AND/OR graphs, and the minimax principle might also extended to use dual heuristics.