{"id":"2506.03066","title":"Provable Reinforcement Learning from Human Feedback with an Unknown Link Function","url":"https://codeofpaper.com/paper/2506.03066","arxiv_url":"https://arxiv.org/abs/2506.03066","published":"2025-06-03","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":1}