reward-scaling-calibration

Fix phantom MaxDD values in training by calibrating reward_scale. Trigger when: (1) validation MaxDD shows 35-80% values, (2) MaxDD doesn't correlate with training quality, (3) gating thresholds seem too lenient/strict.

$ インストール

git clone https://github.com/smith6jt-cop/Skills_Registry /tmp/Skills_Registry && cp -r /tmp/Skills_Registry/plugins/trading/reward-scaling-calibration/skills/reward-scaling-calibration ~/.claude/skills/Skills_Registry

// tip: Run this command in your terminal to install the skill

Repository

smith6jt-cop
smith6jt-cop
Author
smith6jt-cop/Skills_Registry/plugins/trading/reward-scaling-calibration/skills/reward-scaling-calibration
0
Stars
0
Forks
Updated1w ago
Added1w ago