{"author_name":"Paper Radio","author_url":"https://montaan.com/","height":720,"html":"<iframe src=\"https://montaan.com/embed/video/12a20332-bceb-456a-a2bc-7603f8a67f3c\" width=\"1280\" height=\"720\" title=\"Trajectory-Aware Policy Optimization: Closing the State Distribution Gap in Long-Horizon LLM RL — 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://montaan.com/","thumbnail_url":"https://montaan.com/media/episodes/12a20332-bceb-456a-a2bc-7603f8a67f3c/episode.poster.webp","title":"Trajectory-Aware Policy Optimization: Closing the State Distribution Gap in Long-Horizon LLM RL","type":"video","version":"1.0","width":1280}