{"id":"2109.11251","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","url":"https://codeofpaper.com/paper/2109.11251","arxiv_url":"https://arxiv.org/abs/2109.11251","published":"2021-09-23","code":"official","best":{"full_name":"cyanrain7/TRPO-in-MARL","url":"https://github.com/cyanrain7/TRPO-in-MARL","tier":"official","stars":232,"license":"MIT","framework":null,"language":"Python","last_commit":"2023-06-04T14:08:19"},"most_starred_community":null,"implementations":[{"full_name":"cyanrain7/TRPO-in-MARL","url":"https://github.com/cyanrain7/TRPO-in-MARL","tier":"official","stars":232,"license":"MIT","framework":null,"language":"Python","last_commit":"2023-06-04T14:08:19"},{"full_name":"anonymous-ICLR22/Trust-Region-Methods-in-Multi-Agent-Reinforcement-Learning","url":"https://github.com/anonymous-ICLR22/Trust-Region-Methods-in-Multi-Agent-Reinforcement-Learning","tier":"official","stars":11,"license":"MIT","framework":null,"language":"Python","last_commit":"2021-11-29T16:15:34"}],"possible_matches":0}