machine-learningdata-ai
rloo
Reinforcement Learning with Leave-One-Out estimation for policy optimization. Covers RLOOTrainer, reward function integration, baseline estimation, and variance reduction techniques for stable RL training. Includes thinking-aware patterns.
maintainer
atrawog
更新于 1/12/2026
星标
0
分支
0
quick start
Installation and usage
Reinforcement Learning with Leave-One-Out estimation for policy optimization. Covers RLOOTrainer, reward function integration, baseline estimation, and variance reduction techniques for stable RL training. Includes thinking-aware patterns.
安装
$ install --globalskills.sh
使用
安装后，您可以通过在终端运行以下命令来使用此技能：
skills use rloo