Open
Description
What happened + What you expected to happen
I am not sure if this is a bug or my workflow is wrong. I currently initialized a PPOConfig object. PPO only accepts lambda_
not lambda
, but it never assigns lambda_
to self.lambda_
, and AlgorithmConfig
will always refract lambda_
to lambda
, and there are no argument in AlgorithmConfig
for specifying lambda_
. As a result, there is no way for tune
to tune lambda_
or lambda
.
Versions / Dependencies
ray 2.0.0
Reproduction script
As above
Issue Severity
High: It blocks me from completing my task.