{"author_name":"Paper Radio","author_url":"https://montaan.com/","height":480,"html":"<iframe src=\"https://montaan.com/embed/episode/9bbfeb8e-6e1d-46d6-9469-d1d722501252\" width=\"1280\" height=\"480\" title=\"An Online Multiobjective Policy Gradient for Long-run Average-reward Markov Decision Process — 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/9bbfeb8e-6e1d-46d6-9469-d1d722501252/episode.poster.webp","title":"An Online Multiobjective Policy Gradient for Long-run Average-reward Markov Decision Process","type":"rich","version":"1.0","width":1280}