fix: policy steps update in on-policy algorithms

[michele-milesi]

Summary

Describe the purpose of the pull request, including:

• Fix the policy step update for on-policy algorithms: the rollout steps must not be included when updating the policy step (the update is inside the rollout for loop)

Type of Change

Please select the one relevant option below:

• Bug fix (non-breaking change that solves an issue)

Checklist

Please confirm that the following tasks have been completed:

• I have tested my changes locally and they work as expected. (Please describe the tests you performed.)
• I have added unit tests for my changes, or updated existing tests if necessary.
• I have updated the documentation, if applicable.
• I have installed pre-commit and run locally for my code changes.

[belerico]

What if we modify the policy_steps_per_iter to NOT include the rollout-steps? In this case we are more coherent with the rest of the code-base?