WIP: Add action(policy, s) interface to exploration policies
#510
Conversation
This file contains hidden or 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
Member
|
Thanks for the contribution! My only concern is that it goes against the "preferably only one obvious way to do it" wisdom (https://peps.python.org/pep-0020/), since now But I think this is probably OK. I think you should go ahead and implement it for the other policies and I will merge if it looks good. |
Member
|
Is there a name we could use besides |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
To address #497, I extended
EpsGreedyPolicyby internal fields for the greedy policy and the iterationk. If this seems like a reasonable way to go, I can make similar changes toSoftmaxPolicyand edit doc strings. If not feel free to close this PR.With this change both interfaces are supported:
action(p::EpsGreedyPolicy, on_policy::Policy, k, s)action(p::EpsGreedyPolicy, s)