[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-gbpo":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"8ce4c9f0-bf7f-4e96-bf77-e0d3aaaaff96","GBPO","gbpo",1,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"7a04d752-3f1a-4df7-b7c5-8bcb1e69c565","bounded-ratio-reinforcement-learning-ppo-zh","BRRL 取代 PPO 剪裁：BPO 與 GBPO 的穩定性升級","BRRL 把 PPO 的剪裁目標改寫成有界比例框架，推出 BPO 與 GBPO，主打更穩定的更新與更清楚的理論基礎。","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776751794578-t5j7.png","zh","2026-04-21T06:09:39.661696+00:00"]