{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","url":"https://codeofpaper.com/paper/2006.04779","arxiv_url":"https://arxiv.org/abs/2006.04779","published":"2020-06-08","code":"official","best":{"full_name":"aviralkumar2907/CQL","url":"https://github.com/aviralkumar2907/CQL","tier":"official","stars":493,"license":null,"framework":null,"language":"Python","last_commit":"2021-12-07T14:00:25"},"most_starred_community":null,"implementations":[{"full_name":"aviralkumar2907/CQL","url":"https://github.com/aviralkumar2907/CQL","tier":"official","stars":493,"license":null,"framework":null,"language":"Python","last_commit":"2021-12-07T14:00:25"}],"possible_matches":0}