After running the atari_torch.py example, I am able to get good performance on breakout after training for a few epochs. However, when I save the trained model using torch.save(model.state_dict()), then load the model, the same model's performance is poor, and the agent stays to the left side and does not move as opposed to actually playing the game. Any reason why this might be happening?
After running the
atari_torch.py
example, I am able to get good performance on breakout after training for a few epochs. However, when I save the trained model usingtorch.save(model.state_dict())
, then load the model, the same model's performance is poor, and the agent stays to the left side and does not move as opposed to actually playing the game. Any reason why this might be happening?