First Commit

Experimantal/tic_tac_toe/Minimax/minimax.py

@@ -0,0 +1,93 @@
+import random
+
+win_states = [
+    (0, 1, 2), (3, 4, 5), (6, 7, 8),  # horizontal
+    (0, 3, 6), (1, 4, 7), (2, 5, 8),  # vertical
+    (0, 4, 8), (2, 4, 6)  # diagonal
+]
+
+
+def Terminal(state: list):
+    for win_state in win_states:
+        if all(state[i] == "O" for i in win_state) or all(state[i] == "X" for i in win_state):
+            return True
+    if state.count(" ") == 0:
+        return True
+    else:
+        return False
+
+
+def Value(state):
+    for win_state in win_states:
+        if all(state[i] == "O" for i in win_state):
+            return -1
+        elif all(state[i] == "X" for i in win_state):
+            return 1
+    if state.count(" ") == 0:
+        return 0
+
+
+def Player(state: list):
+    if state.count("X") == state.count("O"):
+        return "X"
+    else:
+        return "O"
+
+
+def Actions(state):
+    indexes = []
+    for i in range(9):
+        if state[i] == " ":
+            indexes.append(i)
+    return indexes
+
+
+def Result(state, index, player):
+    state[index] = player
+    return state
+
+
+def Minimax(state):
+    if Terminal(state):
+        return Value(state)
+    if Player(state) == "X":
+        value = -9999
+        for a in Actions(state):
+            value = max(value, Minimax(Result(state.copy(), a, "X")))
+        return value
+
+    elif Player(state) == "O":
+        value = 9999
+        for a in Actions(state):
+            value = min(value, Minimax(Result(state.copy(), a, "O")))
+        return value
+
+
+def aiO(state):
+    best_score = float('inf')
+    best_move = None
+    for move in Actions(state):
+        state[move] = 'O'
+        score = Minimax(state)
+        state[move] = ' '
+        if score < best_score:
+            best_score = score
+            best_move = move
+    return best_move
+
+
+def aiX(state):
+    best_score = float('-inf')
+    best_move = None
+    for move in Actions(state):
+        state[move] = 'X'
+        score = Minimax(state)
+        state[move] = ' '
+        if score > best_score:
+            best_score = score
+            best_move = move
+    return best_move
+
+
+def aiRandom(state):
+    return random.choice(Actions(state))