-
Notifications
You must be signed in to change notification settings - Fork 950
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
add simultaneous node support in policy_aggregator.py and exploitability.py #1034
Conversation
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.
First pass
@@ -228,13 +246,10 @@ def assert_type(cond, msg): | |||
if pid == turn_player: | |||
# update the current node | |||
# will need the observation to query the policies | |||
if state not in self._policy: | |||
if state_key not in self._policy: |
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.
Is this fixing a bug that existed in the code previously?
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.
Yes I believe this should be state_key instead of state. Because state is a pyspiel.state object which doesn't seem right to be a key.
Hi, I found several algorithms like the ones in policy_aggregator.py and exploitability.py didn't handle cases for simultaneous nodes. So this PR is to address this issue.