[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-control":3},{"tag":4,"articles":9},{"id":5,"name":6,"slug":6,"article_count":7,"description_zh":8,"description_en":8},"f33edf72-f878-4348-8f32-425f94135a57","control",0,null,[10],{"id":11,"slug":12,"title":13,"summary":14,"category":15,"image_url":16,"cover_image":16,"language":17,"created_at":18},"55e7197e-f114-4b6c-b3e2-af1a3cd9dfa4","rl-training-hands-off-control-gradually-en","RL Training That Hands Off Control Gradually","This paper shows how to start RL from a working baseline policy and gradually hand control to a learned policy.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780986801034-gf8m.png","en","2026-06-09T06:32:33.516452+00:00"]