-
Notifications
You must be signed in to change notification settings - Fork 5.4k
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
[RLlib] CQL: training iteration function and new buffer API. #24166
Conversation
rllib/utils/replay_buffers/utils.py
Outdated
> 0.0 | ||
) or isinstance( | ||
replay_buffer, MultiAgentPrioritizedReplayBuffer | ||
): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
raise exception if things are configured incorrectly, instead of silently skip the action?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Not in this case, as we simply then don't want to do anything :)
If buffer doesn't support priorities, we'll ignore this call.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hence the comment above:
# Only update priorities if buffer supports them.
…training_itr # Conflicts: # rllib/agents/cql/cql.py
CQL: training iteration function and new buffer API.
@ArturNiederfahrenhorst , ready for review once we have merged your SAC training iteration function PR.
Why are these changes needed?
Related issue number
Checks
scripts/format.sh
to lint the changes in this PR.