evaluation.py

total_epochs, total_penalties = 0, 0
num_of_episodes = 10
enviroment.reset()
counter = 0

for e in range(num_of_episodes):
    state = enviroment.reset()
    state = img_processor.process_env_state(state)
    
    epochs = 0
    penalties = 0
    reward = 0
    total_reward = 0
    
    terminated = False
    
    for timesteps in tqdm(range(timesteps_per_episode)):
        action = agent.act(state)
        state, reward, terminated, info = enviroment.step(action)
        state = img_processor.process_env_state(state)
        
        if reward == -10:
            penalties += 1
        
        total_reward += reward
        epochs += 1
        
        img_processor.save_frame("images/frame_{}.png".format(counter))
        counter += 1
        
    total_penalties += penalties
    total_epochs += epochs

img_processor.makegif("images/")

print("**********************************")
print("Done!")
print("**********************************")