Closed Powercube7 closed 2 years ago
I use stable baselines 3 to train and evaluate the AI
Without more information I cannot debug this issue. I would imagine that it is due to the model and not the gym-super-mario-bros framework.
@Kautenja I think I have one more detail, but that's all I know. This occured when I force stop anything related to the library (model evaluation, prediction, etc.)
When running the following script for the AI to predict an action, the error specified happens. This is my code:
episodes = 5 for episode in range (1, episodes + 1): state = env.reset() done = False score = 0 while not done: env.render() action = model.predict(state) state, reward, done, info = env.step(action) score += reward print('Episode: {}, Score: {}'.format(episode, score)) env.close()