Distinct seeding in data generation

[avocadoali]

No description provided.

[Copilot]

Pull Request Overview

This PR implements distinct seeding for data generation to ensure deterministic and non-overlapping episode generation across train/validation/test splits. The changes replace random seeding with a sequential seeding approach based on episode counts.

• Replaces random seed generation with sequential seeding using start_seed + episode_idx
• Adds configurable env_name parameter to make the script more flexible
• Updates import path to use absolute import for better project structure

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[Copilot]

Pull Request Overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated no new comments.

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[Copilot]

Pull Request Overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated no new comments.

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[emergenz]

Let's confirm what start_level is exactly and whether it has any meaning beyond being a seed (i.e. higher/lower start_levels are just different, but the ordering has no structure in any other way).

[emergenz]

Let's confirm what start_level is exactly and whether it has any meaning beyond being a seed (i.e. higher/lower start_levels are just different, but the ordering has no structure in any other way).

@avocadoali Can you try to confirm the exact role of start_level? Probably easiest to check in the RetroGym/ProcGen paper.