{"id":"2308.02223","title":"ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation","url":"https://codeofpaper.com/paper/2308.02223","arxiv_url":"https://arxiv.org/abs/2308.02223","published":"2023-08-04","code":"community","best":{"full_name":"wangclnlp/DeepSpeed-Chat-Extension","url":"https://github.com/wangclnlp/DeepSpeed-Chat-Extension","tier":"high_confidence_community","stars":21,"license":"Apache-2.0","framework":null,"language":"Python","last_commit":"2024-07-02T15:30:57"},"most_starred_community":null,"implementations":[{"full_name":"wangclnlp/DeepSpeed-Chat-Extension","url":"https://github.com/wangclnlp/DeepSpeed-Chat-Extension","tier":"high_confidence_community","stars":21,"license":"Apache-2.0","framework":null,"language":"Python","last_commit":"2024-07-02T15:30:57"}],"possible_matches":0}