[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-policy-transfer":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"81cccbff-0ee6-49b8-ab24-a7dbedd04fa8","policy transfer","policy-transfer",0,null,[11],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"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"]