← All notes

RL Environments

September 12, 2026 · Updated October 5, 2026

TODO: this note is a placeholder while I work through the material below and write it up properly.

TODO

1. RL Environments, Unsloth
2. “What are RLVR environments for LLMs? | Policy - Rollouts - Rubrics”, Deep Learning with Yacine
3. “One sandbox per rollout, or how labs run RL for agents in 2026”, Sergio Paniego. Look at the suggested readings in this post.
4. XiaomiMiMo/verl, reproduction code for five agentic RL environments.
5. “RL environments for LLM agents: Design, rewards, and validation”, Aryan Kargwal and Jonathan Schlosser.
6. “Environments Hub: A Community Hub To Scale RL To Open AGI”, Prime Intellect Team.
7. MiMo RL Environment Explorer, FineEnvs.