Closed d6y closed 5 years ago
I did use an ale.cfg to set this parameter to 0 and implemented frameskip myself. This was to allow for deterministic behavior based on the random seed.
Le lun. 29 oct. 2018 à 11:53, Richard Dallaway notifications@github.com a écrit :
In the Atari experiment there's a probablistic action repeat (frame skip?):
My reading of this is that the behaviour (or something very similar) is enabled by default in ALE (since 0.5):
When you call self.ale.act(a) for some action a, the action a will be executed right away with a probability (1 - p), otherwise, the action that was previously executed will be executed again. The default value for p right now is 0.25.
^^ from: mgbellemare/Arcade-Learning-Environment#166 (comment) https://github.com/mgbellemare/Arcade-Learning-Environment/issues/166#issuecomment-260140061
I assume it's safe to remove this test from the code (unless there's an ale.cfg in place to disable the default ALE behaviour).
Apologies in advance if I've mised the point :-/ ...still learning.
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/d9w/CGP.jl/issues/12, or mute the thread https://github.com/notifications/unsubscribe-auth/ACkf6DpVMEbV2CJUldM2YMGQY5M3shQBks5upt4XgaJpZM4X-6n6 .
Great! Thanks for clarifying that.
In the Atari experiment there's a probablistic action repeat (frame skip?):
https://github.com/d9w/CGP.jl/blob/d82cc4b48c9c957a971bddea8f8da916824f231f/experiments/atari.jl#L23-L25
My reading of this is that the behaviour (or something very similar) is enabled by default in ALE (since 0.5):
^^ from: https://github.com/mgbellemare/Arcade-Learning-Environment/issues/166#issuecomment-260140061
I assume it's safe to remove this test from the code (unless there's an ale.cfg in place to disable the default ALE behaviour).
Apologies in advance if I've mised the point :-/ ...still learning.