Very interesting paper! After reading your paper, I have two questions I would like to ask you before running your model and I hope you could help. The first question is why the model performance is limited, maybe because the amount of data is not enough? Because I realized that we only have 210, 234, and 122 episodes for treechop, Obtainpickaxe and Obtaindiamond tasks respectively. Another question is how much time do you need to run your model during training? Im using a Nvidia 2070s and Im worried about the training time.
Very interesting paper! After reading your paper, I have two questions I would like to ask you before running your model and I hope you could help. The first question is why the model performance is limited, maybe because the amount of data is not enough? Because I realized that we only have 210, 234, and 122 episodes for treechop, Obtainpickaxe and Obtaindiamond tasks respectively. Another question is how much time do you need to run your model during training? Im using a Nvidia 2070s and Im worried about the training time.