Very clear explanation! The one thing that was a little confusing was why you used self.hp.noise to throttle the deltas in the policy evaluate function but not in the update function.
Sorry to be offtopic but does any of you know a tool to get back into an instagram account..? I was dumb forgot the password. I would appreciate any tips you can give me!
@Benton Hugo I really appreciate your reply. I got to the site on google and I'm trying it out now. Seems to take a while so I will get back to you later with my results.
I'm loving these series, thanks a lot!! I'm also trying to re-code this to gain better understanding, however I'm getting this error: Traceback (most recent call last): File "aug_rand_search.py", line 180, in trainer.train() File "aug_rand_search.py", line 156, in train self.policy.update(rollouts, sigma_rewards) File "aug_rand_search.py", line 84, in update for r_pos, r_neg, delta in rollouts: ValueError: not enough values to unpack (expected 3, got 2) What am I doing wrong? Any help is much appreciated.. thnx
Very clear explanation! The one thing that was a little confusing was why you used self.hp.noise to throttle the deltas in the policy evaluate function but not in the update function.
Great video, explains everything clearly , step by step. Thanks again :)
Thank you brother , I'm a huge fun, I have finally SUBSCRIBED , about time .
I am really glad i found your channel !! I can't thank you enough, really appreciate your amazing effort
Sorry to be offtopic but does any of you know a tool to get back into an instagram account..?
I was dumb forgot the password. I would appreciate any tips you can give me!
@Damon Holden instablaster :)
@Benton Hugo I really appreciate your reply. I got to the site on google and I'm trying it out now.
Seems to take a while so I will get back to you later with my results.
@Benton Hugo It did the trick and I finally got access to my account again. I am so happy!
Thanks so much, you saved my account !
@Damon Holden Happy to help :)
Normalization do not constrain inputs betwen 0 and 1 but rather -1 and 1. Correct ?
Could you share the link for the multiprocessing version?
Can i use it to different things than robots, for example in some games in which i have reward system ?
I'm loving these series, thanks a lot!! I'm also trying to re-code this to gain better understanding, however I'm getting this error:
Traceback (most recent call last):
File "aug_rand_search.py", line 180, in
trainer.train()
File "aug_rand_search.py", line 156, in train
self.policy.update(rollouts, sigma_rewards)
File "aug_rand_search.py", line 84, in update
for r_pos, r_neg, delta in rollouts:
ValueError: not enough values to unpack (expected 3, got 2)
What am I doing wrong? Any help is much appreciated.. thnx
It solved and working! thnx for the upload
Does OpenAI gym work on Linux only? Any equivalent in Windows?