From 8d1ce8e27e5449c9e787c507392844c3e241e933 Mon Sep 17 00:00:00 2001
From: Krasto <alexbuffa22+coder@gmail.com>
Date: Sun, 7 Jan 2024 12:20:27 +0000
Subject: [PATCH] wip minmax

---
 ci_quixo/custom_game.py |  4 ++-
 ci_quixo/minmax.py      | 72 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 75 insertions(+), 1 deletion(-)
 create mode 100644 ci_quixo/minmax.py

diff --git a/ci_quixo/custom_game.py b/ci_quixo/custom_game.py
index 934a086..9d3bd71 100644
--- a/ci_quixo/custom_game.py
+++ b/ci_quixo/custom_game.py
@@ -101,6 +101,8 @@ def from_canon(canon: "CustomGame", idx: int) -> "CustomGame":
         symmetries = canon.symmetries()
         return CustomGame.from_str(symmetries[idx])
     
+    def from_game(game: "Game") -> "CustomGame":
+        return CustomGame.from_board(game.get_board(), game.get_current_player())
 
     def __hash__(self) -> str:
         return str(self).__hash__()
@@ -109,7 +111,7 @@ def __eq__(self, other: "CustomGame") -> bool:
         return self.__hash__() == other.__hash__()
     
     def valid_moves(self, player: int) -> tuple[CompleteMove]:
-        return [it for it in POSSIBLE_MOVES if self._board[it.position] == -1 or self._board[it.position] == player]
+        return [it for it in POSSIBLE_MOVES if self._board[it.position[::-1]] == -1 or self._board[it.position[::-1]] == player]
 
 
 if __name__ == "__main__":
diff --git a/ci_quixo/minmax.py b/ci_quixo/minmax.py
new file mode 100644
index 0000000..032d298
--- /dev/null
+++ b/ci_quixo/minmax.py
@@ -0,0 +1,72 @@
+from game import Player, Game
+from custom_game import CustomGame
+from typing import TYPE_CHECKING
+import numpy as np
+from copy import deepcopy
+import random
+
+if TYPE_CHECKING:
+    from custom_game import CompleteMove
+
+class MinMaxPlayer(Player):
+    
+    def __init__(self, max_depth: int = None, use_alpha_beta_pruning: bool = False) -> None:
+        super().__init__()
+
+        self.max_depth = max_depth
+        self.use_alpha_beta_pruning = use_alpha_beta_pruning
+        self._init_ab()
+
+    def _init_ab(self):
+        self._alpha, self._beta = -np.inf, np.inf
+
+
+    def make_move(self, game: Game) -> "CompleteMove":
+        cg = CustomGame.from_game(game)
+        best_move = self._minmax(0, cg, True)[1]
+        if best_move is None:
+            best_move = random.choice(cg.valid_moves())
+        print("I made a move...")
+        return best_move
+    
+    def _minmax(self, depth: int, game: "CustomGame", maximixe: bool) -> tuple[float, "CompleteMove"]:
+        winner = game.check_winner()
+        if winner != -1:
+            return 25 * winner, None
+        if self.max_depth is not None and depth >= self.max_depth:
+            return 0, None
+
+        if depth == 0:
+            self._init_ab()        
+
+        best_move = None
+        if maximixe:
+            for move in game.valid_moves(game.get_current_player()):
+                copied = deepcopy(game)
+                assert copied._Game__move(*move, copied.current_player_idx), f"Somehow got an invalid move while iterating from valid moves, {copied}, {move}"
+                score, _ = self._minmax(depth+1, copied, False)
+                if score > self._alpha:
+                    self._alpha = score
+                    best_move = move
+                
+                if self.use_alpha_beta_pruning and self._alpha > self._beta:
+                    break
+            return self._alpha, best_move
+        else:
+            for move in game.valid_moves(game.get_current_player()):
+                copied = deepcopy(game)
+                assert copied._Game__move(*move, copied.current_player_idx), "Somehow got an invalid move while iterating from valid moves"
+                score, _ = self._minmax(depth+1, copied, True)
+                if score < self._beta:
+                    self._beta = score
+                    best_move = move
+                
+                if self.use_alpha_beta_pruning and self._alpha > self._beta:
+                    break
+            return self._beta, best_move
+
+if __name__ == "__main__":
+    from main import RandomPlayer
+    mm = MinMaxPlayer(20, True)
+    rp = RandomPlayer()
+    game = Game()
\ No newline at end of file