{"id":"2404.08495","title":"Dataset Reset Policy Optimization for RLHF","url":"https://codeofpaper.com/paper/2404.08495","arxiv_url":"https://arxiv.org/abs/2404.08495","published":"2024-04-12","code":"official","best":{"full_name":"Cornell-RL/drpo","url":"https://github.com/Cornell-RL/drpo","tier":"official","stars":30,"license":"Apache-2.0","framework":null,"language":"Python","last_commit":"2024-04-12T13:53:22"},"most_starred_community":null,"implementations":[{"full_name":"Cornell-RL/drpo","url":"https://github.com/Cornell-RL/drpo","tier":"official","stars":30,"license":"Apache-2.0","framework":null,"language":"Python","last_commit":"2024-04-12T13:53:22"}],"possible_matches":1}