i made a whole neural network but it was depressingly bad. imma try minmax with alphabeta pruning for look ahead

.gitignore

@@ -1 +1,3 @@
 __pycache__/
+env/
+test.py/

connect4_env.py

@@ -1,74 +0,0 @@
-import numpy as np
-
-class Connect4Env:
-    ROWS = 6
-    COLS = 7
-    EMPTY = 0
-    PLAYER1 = 1
-    PLAYER2 = -1
-
-    def __init__(self):
-        self.board = np.zeros((self.ROWS, self.COLS), dtype=np.int8)
-        self.current_player = self.PLAYER1
-
-    def reset(self):
-        self.board[:] = 0
-        self.current_player = self.PLAYER1
-        return self.get_state()
-
-    def get_state(self):
-        return self.board.copy(), self.current_player
-
-    def available_actions(self):
-        return [col for col in range(self.COLS) if self.board[0, col] == 0]
-
-    def step(self, action):
-        if action not in self.available_actions():
-            raise ValueError("Invalid action")
-        
-        for row in reversed(range(self.ROWS)):
-            if self.board[row][action] == 0:
-                self.board[row][action] = self.current_player
-                break
-
-        done, winner = self.check_win()
-        reward = 0
-        if done:
-            if winner == 0:
-                reward = 0  # draw
-            elif winner == self.current_player:
-                reward = 1
-            else:
-                reward = -1
-        self.current_player *= -1
-        return self.get_state(), reward, done
-
-    def check_win(self):
-        for row in range(self.ROWS):
-            for col in range(self.COLS - 3):
-                line = self.board[row, col:col + 4]
-                if abs(sum(line)) == 4:
-                    return True, np.sign(sum(line))
-
-        for row in range(self.ROWS - 3):
-            for col in range(self.COLS):
-                line = self.board[row:row + 4, col]
-                if abs(sum(line)) == 4:
-                    return True, np.sign(sum(line))
-
-        for row in range(self.ROWS - 3):
-            for col in range(self.COLS - 3):
-                diag = [self.board[row + i][col + i] for i in range(4)]
-                if abs(sum(diag)) == 4:
-                    return True, np.sign(sum(diag))
-
-        for row in range(3, self.ROWS):
-            for col in range(self.COLS - 3):
-                diag = [self.board[row - i][col + i] for i in range(4)]
-                if abs(sum(diag)) == 4:
-                    return True, np.sign(sum(diag))
-
-        if all(self.board[0, :] != 0):
-            return True, 0  # draw
-
-        return False, None

main.py

@@ -1,6 +1,5 @@
 import os
 import sys
-import socket
 from colours import Colours as C
 
 # ===========================
@@ -77,11 +76,16 @@ def local_move_provider(player, board):
     col = getIntInput(f"{colourTile(player)} where do you want to drop your tile? 1-7.\n>>> ", board) - 1
     return col
 
-def socket_receive_move(sock):
+def cpu_move_provider(player, board):
-    return int(sock.recv(1024).decode())
     
-def socket_send_move(sock, col):
+    i = 0
-    sock.sendall(str(col).encode())
+    while i < len(board):
+        if any([t == 'O' for t in board[i]]):
+            break
+        else:
+            i += 1
+    print(i)
+    return i
 
 # ===========================
 # |      Main game loop     |
@@ -136,8 +140,7 @@ def play_lan_client():
     return
 
 def play_vs_computer():
-    print("PvC mode coming soon!")
+    play_game(cpu_move_provider, local_move_provider)
-    input("Press Enter to return to menu...")
 
 # ===========================
 # |           Menu          |