Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

prioritized experience replay bug #527

Merged
merged 1 commit into from
Sep 20, 2018
Merged

prioritized experience replay bug #527

merged 1 commit into from
Sep 20, 2018

Conversation

xffxff
Copy link
Contributor

@xffxff xffxff commented Aug 20, 2018

The implementation of prioritized experience replay is a bit wrong. To smaple a minibatch of size k, the range [0, p_total] is divided equally into k ranges. Next, a value is uniformly sampled from each range. Finally the transitions that correspond to each of these sampled values are retrieved from the tree.
Refer to the paper Prioritized Experience Replay. See Appendix B.2.1 for more details

@pzhokhov
Copy link
Collaborator

Looks legit to me... @siemanko, what do you think?

@pzhokhov pzhokhov requested a review from siemanko August 28, 2018 21:29
@pzhokhov pzhokhov merged commit 7859f60 into openai:master Sep 20, 2018
huiwenn pushed a commit to huiwenn/baselines that referenced this pull request Mar 20, 2019
kkonen pushed a commit to kkonen/baselines-1 that referenced this pull request Sep 26, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants