quoridor.policy

Different functions to evaluate the coup to play.

Functions

play_greedy(game)	Evaluate all possibilities and choose best one.
play_random(game[, rng])	Evaluate all possibilities and choose any of them.
play_seeing_future_rec(game[, n_future, n_sim])	Choose coup with best score after playing n coups.
play_with_proba(game[, rng])	Choose one of them based on a exp formula.

quoridor.policy.play_greedy(game)

Evaluate all possibilities and choose best one.

quoridor.policy.play_random(game, rng=None)

Evaluate all possibilities and choose any of them.

quoridor.policy.play_seeing_future_rec(game, n_future=2, n_sim=4)

Choose coup with best score after playing n coups.

quoridor.policy.play_with_proba(game, rng=None)

Choose one of them based on a exp formula.

This formula affect a 0 proba to all play leading to an incorrect situation and e^100 to the best move.