-
Notifications
You must be signed in to change notification settings - Fork 4
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
[RL-baseline] Model v2, original action set, LR 1e-3 #28
Open
ziritrion
wants to merge
21
commits into
RL-with-baseline
Choose a base branch
from
RL-baseline-new-model
base: RL-with-baseline
Could not load branches
Branch not found: {{ refName }}
Could not load tags
Nothing to show
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…sode, successful training)
…-wo-rl into RL-baseline-new-model Trying to solve conflicts
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
We learned that by modifying the learning rate from our original 1e-2 to 1e-3 we could improve the training dramatically.
With Learning Rate of 1e-2 (commit befd201), we could barely pass a Running Reward of 30, as the images below show:
By simply changing the learning rate to 1e-3 we managed to get a Running Reward right below 700 at some points, but noticed a dramatic drop near the 10k episode mark (commit 970f84a)
Here's an example run with the latest model. Notice that the Running Reward achieved by the model at the end of the 10k episodes is about 250 or so, so the behaviour isn't particularly good.
https://user-images.githubusercontent.com/1465235/111752396-f06b4a80-8895-11eb-97c5-4e0a29091cd1.mp4