You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
def reset(self):
"""reset the env."""
self.env.reset()
obs, _, done, _ = self.env.step(1)
if done:
self.env.reset()
obs, _, done, _ = self.env.step(2)
if done:
self.env.reset()
return obs
I don't understand the need to do 3 resets, the choices of actions 1 and 2, and the if done clauses. Also, I don't see how this fully fixes the issue, since for many environments (for example Breakout) the FIRE action must be taken once again after each life loss. Can anyone explain?
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi, can someone please explain to me the following logic? From https://github.com/PyTorchLightning/lightning-bolts/blob/master/pl_bolts/models/rl/common/gym_wrappers.py#L45. My understanding is that this is intended to fix the issue of some games not starting unless the agent takes the FIRE action, leading to some agents staying in the start state forever. But what are these lines of code actually doing?
I don't understand the need to do 3 resets, the choices of actions 1 and 2, and the
if done
clauses. Also, I don't see how this fully fixes the issue, since for many environments (for example Breakout) the FIRE action must be taken once again after each life loss. Can anyone explain?Beta Was this translation helpful? Give feedback.
All reactions