{"author_name":"Paper Radio","author_url":"https://m.montaan.com/","height":720,"html":"<iframe src=\"https://m.montaan.com/embed/video/c366358c-a6b8-4708-a7b6-ae625bb13611\" width=\"1280\" height=\"720\" title=\"Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation — Paper Radio\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture\" allowfullscreen loading=\"lazy\" style=\"border:0;display:block;max-width:100%;\"></iframe>","provider_name":"Paper Radio","provider_url":"https://m.montaan.com/","thumbnail_url":"https://m.montaan.com/media/episodes/c366358c-a6b8-4708-a7b6-ae625bb13611/episode.poster.webp","title":"Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation","type":"video","version":"1.0","width":1280}