[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-trust-region":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"505fad0f-d2b7-4dba-9b01-5e22fb01cd0f","trust region","trust-region",1,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"19f116fd-02dd-4a7d-9638-75a3bb70cae2","bounded-ratio-reinforcement-learning-ppo-en","Why Bounded Ratio RL Replaces PPO's Clipped Objective","BRRL gives PPO a cleaner theory, with BPO and GBPO aiming for more stable policy updates in control and LLM fine-tuning.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776751796218-p4in.png","en","2026-04-21T06:09:40.318224+00:00"]