{"id":"2504.12961","title":"QLLM: Do We Really Need a Mixing Network for Credit Assignment in Multi-Agent Reinforcement Learning?","url":"https://codeofpaper.com/paper/2504.12961","arxiv_url":"https://arxiv.org/abs/2504.12961v5","published":"2025-04-17","code":"official","best":{"full_name":"MaoMaoLYJ/pymarl-qllm","url":"https://github.com/MaoMaoLYJ/pymarl-qllm","tier":"official","stars":2,"license":null,"framework":null,"language":"Python","last_commit":"2026-03-14T05:12:45"},"most_starred_community":{"full_name":"zhouyangjiang71-sys/QLLM","url":"https://github.com/zhouyangjiang71-sys/QLLM","tier":"high_confidence_community","stars":3,"license":null,"framework":null,"language":"Python","last_commit":"2025-12-26T02:42:48"},"implementations":[{"full_name":"MaoMaoLYJ/pymarl-qllm","url":"https://github.com/MaoMaoLYJ/pymarl-qllm","tier":"official","stars":2,"license":null,"framework":null,"language":"Python","last_commit":"2026-03-14T05:12:45"},{"full_name":"zhouyangjiang71-sys/QLLM","url":"https://github.com/zhouyangjiang71-sys/QLLM","tier":"high_confidence_community","stars":3,"license":null,"framework":null,"language":"Python","last_commit":"2025-12-26T02:42:48"}],"possible_matches":3}