Closed Chia-Hsuan-Lee closed 7 years ago
It highly depends on what the game is. If a game needs a long series of steps to make a decision, you need to increase history_length
. If the game's state is diverse, you may need to increase memory_size
. If the game is hard to learn, you need to increase max_steps
. If the input of the game has higher dimension, you need to change the structure of the network to represent the state more clearly.
Thanks really a lot !
Hi i want to run your code to train agent on other games. Is there any code or hyperparameter that needs to be changed in order to train a nice agent ?