{"task":"SMAC+","dataset":"Off_Distant_parallel","metric_names":["Median Win Rate"],"rows":[{"id":84581,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_parallel","model_name":"DRIMA","metrics":{"Median Win Rate":"95.0"},"paper_url":"https://openreview.net/forum?id=5qwA7LLbgP0","paper_title":"Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning","paper_date":"2021-09-29","code_links":[],"metrics_order":"[\"Median Win Rate\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":84582,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_parallel","model_name":"VDN","metrics":{"Median Win Rate":"85.0"},"paper_url":"http://arxiv.org/abs/1706.05296v1","paper_title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning","paper_date":"2017-06-16","code_links":[{"title":"facebookresearch/benchmarl","url":"https://github.com/facebookresearch/benchmarl"},{"title":"tjuhaoxiaotian/pymarl3","url":"https://github.com/tjuhaoxiaotian/pymarl3"},{"title":"hhhusiyi-monash/UPDeT","url":"https://github.com/hhhusiyi-monash/UPDeT"},{"title":"TonghanWang/NDQ","url":"https://github.com/TonghanWang/NDQ"},{"title":"TonghanWang/DOP","url":"https://github.com/TonghanWang/DOP"},{"title":"puyuan1996/MARL","url":"https://github.com/puyuan1996/MARL"},{"title":"Louiii/ValueDecomposition","url":"https://github.com/Louiii/ValueDecomposition"},{"title":"cathyhxh/ctds","url":"https://github.com/cathyhxh/ctds"},{"title":"jugg1er/air","url":"https://github.com/jugg1er/air"},{"title":"jjbong/strangeness_exploration","url":"https://github.com/jjbong/strangeness_exploration"}],"metrics_order":"[\"Median Win Rate\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":84583,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_parallel","model_name":"MASAC","metrics":{"Median Win Rate":"0.0"},"paper_url":"https://arxiv.org/abs/2104.06655v2","paper_title":"Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning","paper_date":"2021-04-14","code_links":[{"title":"puyuan1996/MARL","url":"https://github.com/puyuan1996/MARL"}],"metrics_order":"[\"Median Win Rate\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":84584,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_parallel","model_name":"COMA","metrics":{"Median Win Rate":"0.0"},"paper_url":"https://arxiv.org/abs/1705.08926v3","paper_title":"Counterfactual Multi-Agent Policy Gradients","paper_date":"2017-05-24","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/coma.py"},{"title":"TonghanWang/NDQ","url":"https://github.com/TonghanWang/NDQ"},{"title":"matteokarldonati/Counterfactual-Multi-Agent-Policy-Gradients","url":"https://github.com/matteokarldonati/Counterfactual-Multi-Agent-Policy-Gradients"},{"title":"puyuan1996/MARL","url":"https://github.com/puyuan1996/MARL"},{"title":"nice-hku/cl2marl-smac","url":"https://github.com/nice-hku/cl2marl-smac"},{"title":"hanhanAnderson/LSF-SAC","url":"https://github.com/hanhanAnderson/LSF-SAC"},{"title":"gingkg/smac","url":"https://github.com/gingkg/smac"}],"metrics_order":"[\"Median Win Rate\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":84585,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_parallel","model_name":"IQL","metrics":{"Median Win Rate":"0.0"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Median Win Rate\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":84586,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_parallel","model_name":"QTRAN","metrics":{"Median Win Rate":"0.0"},"paper_url":"https://arxiv.org/abs/1905.05408v1","paper_title":"QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning","paper_date":"2019-05-14","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/qtran.py"},{"title":"hhhusiyi-monash/UPDeT","url":"https://github.com/hhhusiyi-monash/UPDeT"},{"title":"Sonkyunghwan/QTRAN","url":"https://github.com/Sonkyunghwan/QTRAN"},{"title":"jugg1er/air","url":"https://github.com/jugg1er/air"}],"metrics_order":"[\"Median Win Rate\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":84587,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_parallel","model_name":"QMIX","metrics":{"Median Win Rate":"0.0"},"paper_url":"http://arxiv.org/abs/1803.11485v2","paper_title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","paper_date":"2018-03-30","code_links":[{"title":"ray-project/ray","url":"https://github.com/ray-project/ray/tree/master/rllib"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/qmix.py"},{"title":"oxwhirl/pymarl","url":"https://github.com/oxwhirl/pymarl"},{"title":"starry-sky6688/marl-algorithms","url":"https://github.com/starry-sky6688/marl-algorithms"},{"title":"oxwhirl/smac","url":"https://github.com/oxwhirl/smac"},{"title":"facebookresearch/benchmarl","url":"https://github.com/facebookresearch/benchmarl"},{"title":"hhhusiyi-monash/UPDeT","url":"https://github.com/hhhusiyi-monash/UPDeT"},{"title":"TonghanWang/NDQ","url":"https://github.com/TonghanWang/NDQ"},{"title":"nju-rl/acorm","url":"https://github.com/nju-rl/acorm"},{"title":"TonghanWang/DOP","url":"https://github.com/TonghanWang/DOP"},{"title":"puyuan1996/MARL","url":"https://github.com/puyuan1996/MARL"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/qmix"},{"title":"cathyhxh/ctds","url":"https://github.com/cathyhxh/ctds"},{"title":"jugg1er/air","url":"https://github.com/jugg1er/air"},{"title":"ifpen/wfcrl-benchmark","url":"https://github.com/ifpen/wfcrl-benchmark"},{"title":"gingkg/smac","url":"https://github.com/gingkg/smac"},{"title":"15534081591/QMIX","url":"https://github.com/15534081591/QMIX"},{"title":"2023-MindSpore-1/ms-code-221","url":"https://github.com/2023-MindSpore-1/ms-code-221/tree/main/qmix"}],"metrics_order":"[\"Median Win Rate\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":84588,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_parallel","model_name":"DDN","metrics":{"Median Win Rate":"0.0"},"paper_url":"https://arxiv.org/abs/2102.07936v2","paper_title":"DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning","paper_date":"2021-02-16","code_links":[{"title":"j3soon/dfac","url":"https://github.com/j3soon/dfac"}],"metrics_order":"[\"Median Win Rate\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":84589,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_parallel","model_name":"DIQL","metrics":{"Median Win Rate":"0.0"},"paper_url":"https://arxiv.org/abs/2102.07936v2","paper_title":"DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning","paper_date":"2021-02-16","code_links":[{"title":"j3soon/dfac","url":"https://github.com/j3soon/dfac"}],"metrics_order":"[\"Median Win Rate\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":84590,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_parallel","model_name":"DMIX","metrics":{"Median Win Rate":"0.0"},"paper_url":"https://arxiv.org/abs/2102.07936v2","paper_title":"DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning","paper_date":"2021-02-16","code_links":[{"title":"j3soon/dfac","url":"https://github.com/j3soon/dfac"}],"metrics_order":"[\"Median Win Rate\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":128537,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_parallel","model_name":"DRIMA","metrics":{"Median Win Rate":"95.0"},"paper_url":"https://openreview.net/forum?id=5qwA7LLbgP0","paper_title":"Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning","paper_date":"2021-09-29","code_links":[],"metrics_order":"[\"Median Win Rate\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":128538,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_parallel","model_name":"VDN","metrics":{"Median Win Rate":"85.0"},"paper_url":"http://arxiv.org/abs/1706.05296v1","paper_title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning","paper_date":"2017-06-16","code_links":[{"title":"facebookresearch/benchmarl","url":"https://github.com/facebookresearch/benchmarl"},{"title":"tjuhaoxiaotian/pymarl3","url":"https://github.com/tjuhaoxiaotian/pymarl3"},{"title":"hhhusiyi-monash/UPDeT","url":"https://github.com/hhhusiyi-monash/UPDeT"},{"title":"TonghanWang/NDQ","url":"https://github.com/TonghanWang/NDQ"},{"title":"TonghanWang/DOP","url":"https://github.com/TonghanWang/DOP"},{"title":"puyuan1996/MARL","url":"https://github.com/puyuan1996/MARL"},{"title":"Louiii/ValueDecomposition","url":"https://github.com/Louiii/ValueDecomposition"},{"title":"cathyhxh/ctds","url":"https://github.com/cathyhxh/ctds"},{"title":"jugg1er/air","url":"https://github.com/jugg1er/air"},{"title":"jjbong/strangeness_exploration","url":"https://github.com/jjbong/strangeness_exploration"}],"metrics_order":"[\"Median Win Rate\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":128539,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_parallel","model_name":"MASAC","metrics":{"Median Win Rate":"0.0"},"paper_url":"https://arxiv.org/abs/2104.06655v2","paper_title":"Decomposed Soft Actor-Critic Method for Cooperative Multi-Agent Reinforcement Learning","paper_date":"2021-04-14","code_links":[{"title":"puyuan1996/MARL","url":"https://github.com/puyuan1996/MARL"}],"metrics_order":"[\"Median Win Rate\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":128540,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_parallel","model_name":"COMA","metrics":{"Median Win Rate":"0.0"},"paper_url":"https://arxiv.org/abs/1705.08926v3","paper_title":"Counterfactual Multi-Agent Policy Gradients","paper_date":"2017-05-24","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/coma.py"},{"title":"TonghanWang/NDQ","url":"https://github.com/TonghanWang/NDQ"},{"title":"matteokarldonati/Counterfactual-Multi-Agent-Policy-Gradients","url":"https://github.com/matteokarldonati/Counterfactual-Multi-Agent-Policy-Gradients"},{"title":"puyuan1996/MARL","url":"https://github.com/puyuan1996/MARL"},{"title":"nice-hku/cl2marl-smac","url":"https://github.com/nice-hku/cl2marl-smac"},{"title":"hanhanAnderson/LSF-SAC","url":"https://github.com/hanhanAnderson/LSF-SAC"},{"title":"gingkg/smac","url":"https://github.com/gingkg/smac"}],"metrics_order":"[\"Median Win Rate\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":128541,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_parallel","model_name":"IQL","metrics":{"Median Win Rate":"0.0"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Median Win Rate\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":128542,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_parallel","model_name":"QTRAN","metrics":{"Median Win Rate":"0.0"},"paper_url":"https://arxiv.org/abs/1905.05408v1","paper_title":"QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning","paper_date":"2019-05-14","code_links":[{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/qtran.py"},{"title":"hhhusiyi-monash/UPDeT","url":"https://github.com/hhhusiyi-monash/UPDeT"},{"title":"Sonkyunghwan/QTRAN","url":"https://github.com/Sonkyunghwan/QTRAN"},{"title":"jugg1er/air","url":"https://github.com/jugg1er/air"}],"metrics_order":"[\"Median Win Rate\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":128543,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_parallel","model_name":"QMIX","metrics":{"Median Win Rate":"0.0"},"paper_url":"http://arxiv.org/abs/1803.11485v2","paper_title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","paper_date":"2018-03-30","code_links":[{"title":"ray-project/ray","url":"https://github.com/ray-project/ray/tree/master/rllib"},{"title":"opendilab/DI-engine","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/qmix.py"},{"title":"oxwhirl/pymarl","url":"https://github.com/oxwhirl/pymarl"},{"title":"starry-sky6688/marl-algorithms","url":"https://github.com/starry-sky6688/marl-algorithms"},{"title":"oxwhirl/smac","url":"https://github.com/oxwhirl/smac"},{"title":"facebookresearch/benchmarl","url":"https://github.com/facebookresearch/benchmarl"},{"title":"hhhusiyi-monash/UPDeT","url":"https://github.com/hhhusiyi-monash/UPDeT"},{"title":"TonghanWang/NDQ","url":"https://github.com/TonghanWang/NDQ"},{"title":"nju-rl/acorm","url":"https://github.com/nju-rl/acorm"},{"title":"TonghanWang/DOP","url":"https://github.com/TonghanWang/DOP"},{"title":"puyuan1996/MARL","url":"https://github.com/puyuan1996/MARL"},{"title":"xiuyu0000/new_papers_codes","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/qmix"},{"title":"cathyhxh/ctds","url":"https://github.com/cathyhxh/ctds"},{"title":"jugg1er/air","url":"https://github.com/jugg1er/air"},{"title":"ifpen/wfcrl-benchmark","url":"https://github.com/ifpen/wfcrl-benchmark"},{"title":"gingkg/smac","url":"https://github.com/gingkg/smac"},{"title":"15534081591/QMIX","url":"https://github.com/15534081591/QMIX"},{"title":"2023-MindSpore-1/ms-code-221","url":"https://github.com/2023-MindSpore-1/ms-code-221/tree/main/qmix"}],"metrics_order":"[\"Median Win Rate\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":128544,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_parallel","model_name":"DDN","metrics":{"Median Win Rate":"0.0"},"paper_url":"https://arxiv.org/abs/2102.07936v2","paper_title":"DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning","paper_date":"2021-02-16","code_links":[{"title":"j3soon/dfac","url":"https://github.com/j3soon/dfac"}],"metrics_order":"[\"Median Win Rate\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":128545,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_parallel","model_name":"DIQL","metrics":{"Median Win Rate":"0.0"},"paper_url":"https://arxiv.org/abs/2102.07936v2","paper_title":"DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning","paper_date":"2021-02-16","code_links":[{"title":"j3soon/dfac","url":"https://github.com/j3soon/dfac"}],"metrics_order":"[\"Median Win Rate\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":128546,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_parallel","model_name":"DMIX","metrics":{"Median Win Rate":"0.0"},"paper_url":"https://arxiv.org/abs/2102.07936v2","paper_title":"DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning","paper_date":"2021-02-16","code_links":[{"title":"j3soon/dfac","url":"https://github.com/j3soon/dfac"}],"metrics_order":"[\"Median Win Rate\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]}]}