home/categories/education/openpipe-art-agents-skills-train-rl-skill-md
educationdocumentation

train-rl

RL training reference for the ART framework. Use when the user asks to create, write, or help with an RL training script, reinforcement learning, GRPO, reward functions, RULER scoring, rollout functions, or anything related to RL fine-tuning.

OpenPipe
maintainer
OpenPipe
更新日 3/27/2026
スター
9154
フォーク
790
quick start

Installation and usage

RL training reference for the ART framework. Use when the user asks to create, write, or help with an RL training script, reinforcement learning, GRPO, reward functions, RULER scoring, rollout functions, or anything related to RL fine-tuning.

インストール
$ install --globalskills.sh
使い方

インストール後、ターミナルで以下のコマンドを実行してこのスキルを使用できます:

skills use train-rl