Avoid bad RLlib logs on init

[Mark2000]

Description

RLlib logging wrapper logs some weird data immediately after starting RLlib. This code avoids those logs. I don't love this code, but it's better than nothing.

Type of change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)

How should this pull request be reviewed?

• By commit
• All changes at once

How Has This Been Tested?

RLlib code not covered by tests.

Future Work

None.

Checklist

• I have performed a self-review of my code
• I have commented my code in hard-to-understand areas
• I have made corresponding changes to the documentation and release notes
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works

[Copilot]

Pull Request Overview

This PR adds a mechanism to skip initial logging during environment resets to prevent unwanted log entries on the first reset. The implementation uses a counter that decrements on each reset until reaching zero, after which normal logging resumes.

• Introduces a logs_to_skip counter initialized to 3 to suppress logging on initial resets
• Modifies the reset() method to conditionally call log_data_on_reset() based on the counter

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Yume27]

Do you have any reason why you chose 3 for that?

[Mark2000]

Trial and error. Tried to find a more robust way of telling reset() calls during algorithm initialization from calls during training, but there wasn't an obvious way of distinguishing them and–at least for PPO–3 is the magic number.