The horizon effect is a problem in artificial intelligence where, in many games, the number of possible states or positions is immense and computers can only feasibly search a small portion of it, typically a few ply down the game tree. Thus, for a computer searching only five ply, there is a possibility that it will make a move which is detrimental, but the detrimental effect is not visible because it does not search to the depth of the error (i.e. beyond its horizon).
When evaluating a large game tree using techniques such as minimax or alpha-beta pruning, search depth is limited for feasibility reasons. However, evaluating a partial tree may give a misleading result. When a significant change exists just over the 'horizon' of the search depth, the computational device falls victim to the horizon effect.
The horizon effect can be mitigated by extending the search algorithm with a quiescence search. This gives the search algorithm ability to look beyond its horizon for a certain class of moves of major importance to the game state, such as captures.
Rewriting the evaluation function for leaf nodes and/or analyzing sufficiently more nodes will solve many horizon effect problems.
Read more about Horizon Effect: Example
Famous quotes containing the words horizon and/or effect:
“In expanding the field of knowledge, we but increase the horizon of ignorance.”
—Henry Miller (1891–1980)
“Nothing could his enemies do but it rebounded to his infinite advantage,—that is, to the advantage of his cause.... No theatrical manager could have arranged things so wisely to give effect to his behavior and words. And who, think you, was the manager? Who placed the slave-woman and her child, whom he stooped to kiss for a symbol, between his prison and the gallows?”
—Henry David Thoreau (1817–1862)