{"id":"2005.12729","title":"Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO","url":"https://codeofpaper.com/paper/2005.12729","arxiv_url":"https://arxiv.org/abs/2005.12729","published":"2020-05-25","code":"official","best":{"full_name":"MadryLab/implementation-matters","url":"https://github.com/MadryLab/implementation-matters","tier":"official","stars":140,"license":"MIT","framework":null,"language":"Python","last_commit":"2024-07-25T10:12:51"},"most_starred_community":null,"implementations":[{"full_name":"MadryLab/implementation-matters","url":"https://github.com/MadryLab/implementation-matters","tier":"official","stars":140,"license":"MIT","framework":null,"language":"Python","last_commit":"2024-07-25T10:12:51"}],"possible_matches":0}