Notes
Technical notes, experiment logs, debugging journals, and everything else.
Use _template.qmd as a starting point for new entries.
| Date | Note | Tags | Summary |
|---|---|---|---|
| Mar 12, 2026 | Designing your own RL engine | tutorial | In this post, we’ll guide you step by step through designing your own asynchronous, distributed reinforcement learning (RL) engine purpose-built for post-training large… |
| Mar 12, 2026 | Notes on verl | engineering | These are some preliminary rough draft notes on verl. |
| Feb 26, 2026 | GRPO Training Pipeline Setup Notes | rl, medenv, infra | Technical setup notes for the GRPO training pipeline on MedEnv tasks. |
No matching items