Update app.py

app.py

@@ -1,8 +1,3 @@
-# app.py
-# =============
-# This is a complete app.py file for an Arkanoid game that a neural network will play and learn using reinforcement learning.
-# The game is built using pygame, and the neural network is trained using stable-baselines3. Gradio is used for the interface.
-
 import os
 import numpy as np
 import pygame
@@ -12,7 +7,6 @@ from stable_baselines3 import DQN
 from stable_baselines3.common.evaluation import evaluate_policy
 import gradio as gr
 import cv2
-import imageio
 
 # Constants
 SCREEN_WIDTH = 640
@@ -68,7 +62,7 @@ class Ball:
 
 class Brick:
     def __init__(self, x, y):
-        self.rect = pygame.Rect(x, y, BRICK_WIDTH, BRICK_HEIGHT)
+        self.rect = pygame.Rect(x, y, BRICK_WIDTH - 5, BRICK_HEIGHT - 5)
 
 class ArkanoidEnv(gym.Env):
     def __init__(self):
@@ -85,7 +79,8 @@ class ArkanoidEnv(gym.Env):
             self.seed_value = seed
         self.paddle = Paddle()
         self.ball = Ball()
-        self.bricks = [Brick(x, y) for y in range(BRICK_HEIGHT, BRICK_HEIGHT * (BRICK_ROWS + 1), BRICK_HEIGHT) for x in range(BRICK_WIDTH, SCREEN_WIDTH - BRICK_WIDTH, BRICK_WIDTH)]
+        self.bricks = [Brick(x, y) for y in range(BRICK_HEIGHT, BRICK_HEIGHT * (BRICK_ROWS + 1), BRICK_HEIGHT) 
+                       for x in range(BRICK_WIDTH, SCREEN_WIDTH - BRICK_WIDTH, BRICK_WIDTH)]
         self.done = False
         self.score = 0
         return self._get_state(), {}
@@ -172,27 +167,27 @@ def train_and_play():
 
     for i in range(0, total_timesteps, timesteps_per_update):
         model.learn(total_timesteps=timesteps_per_update)
-        obs = env.reset()[0]
+        obs, _ = env.reset()
         done = False
         truncated = False
         while not done and not truncated:
             action, _states = model.predict(obs, deterministic=True)
-            obs, reward, done, truncated, info = env.step(action)
+            obs, reward, done, truncated, _ = env.step(action)
             env.render()
             # Capture the current frame
             frame = pygame.surfarray.array3d(pygame.display.get_surface())
+            frame = np.rot90(frame)  # Fix orientation
             frame = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR)
             video_frames.append(frame)
 
     # Save the video
     video_path = "arkanoid_training.mp4"
-    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
-    video_writer = cv2.VideoWriter(video_path, fourcc, FPS, (SCREEN_WIDTH, SCREEN_HEIGHT))
+    video_writer = cv2.VideoWriter(video_path, cv2.VideoWriter_fourcc(*'mp4v'), FPS, (SCREEN_WIDTH, SCREEN_HEIGHT))
     for frame in video_frames:
         video_writer.write(frame)
     video_writer.release()
 
-    # Return the video path
+    env.close()  # Ensure the environment is properly closed
     return video_path
 
 # Main function
@@ -208,17 +203,3 @@ def main():
 
 if __name__ == "__main__":
     main()
-
-# Dependencies
-# =============
-# The following dependencies are required to run this app:
-# - pygame
-# - stable-baselines3
-# - torch
-# - gradio
-# - gymnasium
-# - opencv-python
-# - imageio
-#
-# You can install these dependencies using pip:
-# pip install pygame stable-baselines3 torch gradio gymnasium opencv-python imageio