{"id":"2306.09526","title":"Residual Q-Learning: Offline and Online Policy Customization without Value","url":"https://codeofpaper.com/paper/2306.09526","arxiv_url":"https://arxiv.org/abs/2306.09526","published":"2023-06-15","code":"community","best":{"full_name":"chenran-li/RQL-release","url":"https://github.com/chenran-li/RQL-release","tier":"high_confidence_community","stars":36,"license":null,"framework":null,"language":"Python","last_commit":"2024-03-29T04:28:06"},"most_starred_community":null,"implementations":[{"full_name":"chenran-li/RQL-release","url":"https://github.com/chenran-li/RQL-release","tier":"high_confidence_community","stars":36,"license":null,"framework":null,"language":"Python","last_commit":"2024-03-29T04:28:06"}],"possible_matches":1}