{"task":"SMAC+","dataset":"Off_Distant_sequential","metric_names":["Median Win Rate"],"rows":[{"id":84601,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_sequential","model_name":"DRIMA","metrics":{"Median Win Rate":"100"},"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":84602,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_sequential","model_name":"QMIX","metrics":{"Median Win Rate":"93.8"},"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":84603,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_sequential","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":84604,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_sequential","model_name":"MADDPG","metrics":{"Median Win Rate":"0.0"},"paper_url":"https://arxiv.org/abs/1706.02275v4","paper_title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","paper_date":"2017-06-07","code_links":[{"title":"ray-project/ray","url":"https://github.com/ray-project/ray/tree/master/rllib"},{"title":"openai/multiagent-particle-envs","url":"https://github.com/openai/multiagent-particle-envs"},{"title":"openai/maddpg","url":"https://github.com/openai/maddpg"},{"title":"xuehy/pytorch-maddpg","url":"https://github.com/xuehy/pytorch-maddpg"},{"title":"shariqiqbal2810/maddpg-pytorch","url":"https://github.com/shariqiqbal2810/maddpg-pytorch"},{"title":"starry-sky6688/MADDPG","url":"https://github.com/starry-sky6688/MADDPG"},{"title":"facebookresearch/benchmarl","url":"https://github.com/facebookresearch/benchmarl"},{"title":"philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients","url":"https://github.com/philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients"},{"title":"cyanrain7/trpo-in-marl","url":"https://github.com/cyanrain7/trpo-in-marl"},{"title":"cyanrain7/trust-region-policy-optimisation-in-multi-agent-reinforcement-learning","url":"https://github.com/cyanrain7/trust-region-policy-optimisation-in-multi-agent-reinforcement-learning"},{"title":"JohannesAck/tf2multiagentrl","url":"https://github.com/JohannesAck/tf2multiagentrl"},{"title":"isp1tze/MAProj","url":"https://github.com/isp1tze/MAProj"},{"title":"JohannesAck/MATD3implementation","url":"https://github.com/JohannesAck/MATD3implementation"},{"title":"thechrisyoon08/Multi-agent-reinforcement-learning","url":"https://github.com/thechrisyoon08/Multi-agent-reinforcement-learning"},{"title":"thechrisyoon08/marl","url":"https://github.com/thechrisyoon08/marl"},{"title":"cyoon1729/Multi-agent-reinforcement-learning","url":"https://github.com/cyoon1729/Multi-agent-reinforcement-learning"},{"title":"quantumiracle/mars","url":"https://github.com/quantumiracle/mars"},{"title":"shariqiqbal2810/multiagent-particle-envs","url":"https://github.com/shariqiqbal2810/multiagent-particle-envs"},{"title":"morning9393/HAPPO-HATRPO","url":"https://github.com/morning9393/HAPPO-HATRPO"},{"title":"google/maddpg-replication","url":"https://github.com/google/maddpg-replication"},{"title":"caslab-vt/SARNet","url":"https://github.com/caslab-vt/SARNet"},{"title":"qi-pang/mdpfuzz","url":"https://github.com/qi-pang/mdpfuzz"},{"title":"pr-shukla/maddpg-keras","url":"https://github.com/pr-shukla/maddpg-keras"},{"title":"gingkg/multiagent-particle-envs","url":"https://github.com/gingkg/multiagent-particle-envs"},{"title":"jyqhahah/rl_maddpg_matd3","url":"https://github.com/jyqhahah/rl_maddpg_matd3"},{"title":"baoqianwang/iros22_darl1n","url":"https://github.com/baoqianwang/iros22_darl1n"},{"title":"zowiezhang/stas","url":"https://github.com/zowiezhang/stas"},{"title":"yannbouteiller/gym-airsimdroneracinglab","url":"https://github.com/yannbouteiller/gym-airsimdroneracinglab"},{"title":"anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning","url":"https://github.com/anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning"},{"title":"schroederdewitt/multiagent-particle-envs","url":"https://github.com/schroederdewitt/multiagent-particle-envs"},{"title":"EyaRhouma/collaboration-competition-MADDPG","url":"https://github.com/EyaRhouma/collaboration-competition-MADDPG"},{"title":"zoeyuchao/MPE-pytorch","url":"https://github.com/zoeyuchao/MPE-pytorch"},{"title":"bonniesjli/MADDPG_Tennis","url":"https://github.com/bonniesjli/MADDPG_Tennis"},{"title":"bonniesjli/MADDPG_Tennis_UnityML","url":"https://github.com/bonniesjli/MADDPG_Tennis_UnityML"},{"title":"semitable/multiagent-particle-envs","url":"https://github.com/semitable/multiagent-particle-envs"},{"title":"kargarisaac/macrpo","url":"https://github.com/kargarisaac/macrpo"},{"title":"madras-simulator/Multi-Agent-Particle-Environment","url":"https://github.com/madras-simulator/Multi-Agent-Particle-Environment"},{"title":"wsjeon/multiagent-particle-envs-maac","url":"https://github.com/wsjeon/multiagent-particle-envs-maac"},{"title":"NeuroCSUT/intentions","url":"https://github.com/NeuroCSUT/intentions"},{"title":"marwanihab/RL_Tag_Game","url":"https://github.com/marwanihab/RL_Tag_Game"},{"title":"zoeyuchao/MPEnew-pytorch","url":"https://github.com/zoeyuchao/MPEnew-pytorch"},{"title":"lachisis/multiagent-particle-envs","url":"https://github.com/lachisis/multiagent-particle-envs"},{"title":"Stippler/cow-simulator","url":"https://github.com/Stippler/cow-simulator"},{"title":"biorobotics/PRD_environments","url":"https://github.com/biorobotics/PRD_environments"},{"title":"raoshashank/Tennis-with-MADDPG","url":"https://github.com/raoshashank/Tennis-with-MADDPG"},{"title":"Steven-Ho/multiagent-particle-envs","url":"https://github.com/Steven-Ho/multiagent-particle-envs"},{"title":"sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3","url":"https://github.com/sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3"},{"title":"Ah31/maddpg_pytorch","url":"https://github.com/Ah31/maddpg_pytorch"},{"title":"karishnu/tf-agents-multi-particle-envs","url":"https://github.com/karishnu/tf-agents-multi-particle-envs"},{"title":"SihongHo/multiagent-particle-envs","url":"https://github.com/SihongHo/multiagent-particle-envs"},{"title":"wsjeon/multiagent-particle-envs-v2","url":"https://github.com/wsjeon/multiagent-particle-envs-v2"},{"title":"baicenxiao/shaping-advice","url":"https://github.com/baicenxiao/shaping-advice"},{"title":"Yutongamber/MADDPG","url":"https://github.com/Yutongamber/MADDPG"},{"title":"SintolRTOS/multi-agent_Example","url":"https://github.com/SintolRTOS/multi-agent_Example"},{"title":"Chan1998/MAAC","url":"https://github.com/Chan1998/MAAC"},{"title":"Abdelhamid-bouzid/Multi-Agent-Deep-Deterministic-Policy-Gradient","url":"https://github.com/Abdelhamid-bouzid/Multi-Agent-Deep-Deterministic-Policy-Gradient"},{"title":"debajit15kgp/multiagent-envs","url":"https://github.com/debajit15kgp/multiagent-envs"},{"title":"johannesharmse/multi_agent_RL","url":"https://github.com/johannesharmse/multi_agent_RL"},{"title":"jingdic/rgmcomm","url":"https://github.com/jingdic/rgmcomm"},{"title":"rainandwind1/Maddpg_multiagent","url":"https://github.com/rainandwind1/Maddpg_multiagent"},{"title":"kishorkuttan/Multi-Agent-Deep-Deterministic-Policy-Gradient-actor-critic-deep-reinforcement-for-capacity-manageme","url":"https://github.com/kishorkuttan/Multi-Agent-Deep-Deterministic-Policy-Gradient-actor-critic-deep-reinforcement-for-capacity-manageme"},{"title":"dtabas/multiagent-particle-envs","url":"https://github.com/dtabas/multiagent-particle-envs"},{"title":"goldbattle/snakes_mal","url":"https://github.com/goldbattle/snakes_mal"},{"title":"ksajan/DDPG-MAPE","url":"https://github.com/ksajan/DDPG-MAPE"},{"title":"rainandwind1/MERL","url":"https://github.com/rainandwind1/MERL"},{"title":"darshil333/CSE574","url":"https://github.com/darshil333/CSE574"},{"title":"rallen10/multiagent-particle-envs","url":"https://github.com/rallen10/multiagent-particle-envs"},{"title":"tkarr21/multagent-particle-envs","url":"https://github.com/tkarr21/multagent-particle-envs"},{"title":"mauricemager/multiagent-robot","url":"https://github.com/mauricemager/multiagent-robot"},{"title":"tkarr21/multiagent-particle-envs","url":"https://github.com/tkarr21/multiagent-particle-envs"},{"title":"petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity","url":"https://github.com/petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity"},{"title":"MrDaubinet/collaboration-and-competition","url":"https://github.com/MrDaubinet/collaboration-and-competition"},{"title":"LXYYY/multiagent-particle-envs","url":"https://github.com/LXYYY/multiagent-particle-envs"},{"title":"Zorrorulz/MultiAgentDDPG-Tennis","url":"https://github.com/Zorrorulz/MultiAgentDDPG-Tennis"},{"title":"biemann/Collaboration-and-Competition","url":"https://github.com/biemann/Collaboration-and-Competition"},{"title":"hepengli/multiagent-particle-envs","url":"https://github.com/hepengli/multiagent-particle-envs"},{"title":"jiayu-ch15/MPE-for-curriculum-learning","url":"https://github.com/jiayu-ch15/MPE-for-curriculum-learning"},{"title":"marwanihab/RL_Testing_Noise_ASRN","url":"https://github.com/marwanihab/RL_Testing_Noise_ASRN"},{"title":"AleXander-Tsui/MPE","url":"https://github.com/AleXander-Tsui/MPE"},{"title":"madhur-tandon/RL-Project","url":"https://github.com/madhur-tandon/RL-Project"},{"title":"rainandwind1/MADDPG-reconstruct","url":"https://github.com/rainandwind1/MADDPG-reconstruct"},{"title":"RL-WFU/multi_agent_attack","url":"https://github.com/RL-WFU/multi_agent_attack"},{"title":"JinTanda/MADDPG_env","url":"https://github.com/JinTanda/MADDPG_env"},{"title":"jansenkeith501/CS295-MADDPG","url":"https://github.com/jansenkeith501/CS295-MADDPG"},{"title":"baradist/multiagent-particle-envs","url":"https://github.com/baradist/multiagent-particle-envs"},{"title":"krasing/DRLearningCollaboration","url":"https://github.com/krasing/DRLearningCollaboration"}],"metrics_order":"[\"Median Win Rate\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]},{"id":128557,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_sequential","model_name":"DRIMA","metrics":{"Median Win Rate":"100"},"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":128558,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_sequential","model_name":"QMIX","metrics":{"Median Win Rate":"93.8"},"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":128559,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_sequential","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":128560,"task":"SMAC+","parent_task":"SMAC","dataset":"Off_Distant_sequential","model_name":"MADDPG","metrics":{"Median Win Rate":"0.0"},"paper_url":"https://arxiv.org/abs/1706.02275v4","paper_title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","paper_date":"2017-06-07","code_links":[{"title":"ray-project/ray","url":"https://github.com/ray-project/ray/tree/master/rllib"},{"title":"openai/multiagent-particle-envs","url":"https://github.com/openai/multiagent-particle-envs"},{"title":"openai/maddpg","url":"https://github.com/openai/maddpg"},{"title":"xuehy/pytorch-maddpg","url":"https://github.com/xuehy/pytorch-maddpg"},{"title":"shariqiqbal2810/maddpg-pytorch","url":"https://github.com/shariqiqbal2810/maddpg-pytorch"},{"title":"starry-sky6688/MADDPG","url":"https://github.com/starry-sky6688/MADDPG"},{"title":"facebookresearch/benchmarl","url":"https://github.com/facebookresearch/benchmarl"},{"title":"philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients","url":"https://github.com/philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients"},{"title":"cyanrain7/trpo-in-marl","url":"https://github.com/cyanrain7/trpo-in-marl"},{"title":"cyanrain7/trust-region-policy-optimisation-in-multi-agent-reinforcement-learning","url":"https://github.com/cyanrain7/trust-region-policy-optimisation-in-multi-agent-reinforcement-learning"},{"title":"JohannesAck/tf2multiagentrl","url":"https://github.com/JohannesAck/tf2multiagentrl"},{"title":"isp1tze/MAProj","url":"https://github.com/isp1tze/MAProj"},{"title":"JohannesAck/MATD3implementation","url":"https://github.com/JohannesAck/MATD3implementation"},{"title":"thechrisyoon08/Multi-agent-reinforcement-learning","url":"https://github.com/thechrisyoon08/Multi-agent-reinforcement-learning"},{"title":"thechrisyoon08/marl","url":"https://github.com/thechrisyoon08/marl"},{"title":"cyoon1729/Multi-agent-reinforcement-learning","url":"https://github.com/cyoon1729/Multi-agent-reinforcement-learning"},{"title":"quantumiracle/mars","url":"https://github.com/quantumiracle/mars"},{"title":"shariqiqbal2810/multiagent-particle-envs","url":"https://github.com/shariqiqbal2810/multiagent-particle-envs"},{"title":"morning9393/HAPPO-HATRPO","url":"https://github.com/morning9393/HAPPO-HATRPO"},{"title":"google/maddpg-replication","url":"https://github.com/google/maddpg-replication"},{"title":"caslab-vt/SARNet","url":"https://github.com/caslab-vt/SARNet"},{"title":"qi-pang/mdpfuzz","url":"https://github.com/qi-pang/mdpfuzz"},{"title":"pr-shukla/maddpg-keras","url":"https://github.com/pr-shukla/maddpg-keras"},{"title":"gingkg/multiagent-particle-envs","url":"https://github.com/gingkg/multiagent-particle-envs"},{"title":"jyqhahah/rl_maddpg_matd3","url":"https://github.com/jyqhahah/rl_maddpg_matd3"},{"title":"baoqianwang/iros22_darl1n","url":"https://github.com/baoqianwang/iros22_darl1n"},{"title":"zowiezhang/stas","url":"https://github.com/zowiezhang/stas"},{"title":"yannbouteiller/gym-airsimdroneracinglab","url":"https://github.com/yannbouteiller/gym-airsimdroneracinglab"},{"title":"anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning","url":"https://github.com/anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning"},{"title":"schroederdewitt/multiagent-particle-envs","url":"https://github.com/schroederdewitt/multiagent-particle-envs"},{"title":"EyaRhouma/collaboration-competition-MADDPG","url":"https://github.com/EyaRhouma/collaboration-competition-MADDPG"},{"title":"zoeyuchao/MPE-pytorch","url":"https://github.com/zoeyuchao/MPE-pytorch"},{"title":"bonniesjli/MADDPG_Tennis","url":"https://github.com/bonniesjli/MADDPG_Tennis"},{"title":"bonniesjli/MADDPG_Tennis_UnityML","url":"https://github.com/bonniesjli/MADDPG_Tennis_UnityML"},{"title":"semitable/multiagent-particle-envs","url":"https://github.com/semitable/multiagent-particle-envs"},{"title":"kargarisaac/macrpo","url":"https://github.com/kargarisaac/macrpo"},{"title":"madras-simulator/Multi-Agent-Particle-Environment","url":"https://github.com/madras-simulator/Multi-Agent-Particle-Environment"},{"title":"wsjeon/multiagent-particle-envs-maac","url":"https://github.com/wsjeon/multiagent-particle-envs-maac"},{"title":"NeuroCSUT/intentions","url":"https://github.com/NeuroCSUT/intentions"},{"title":"marwanihab/RL_Tag_Game","url":"https://github.com/marwanihab/RL_Tag_Game"},{"title":"zoeyuchao/MPEnew-pytorch","url":"https://github.com/zoeyuchao/MPEnew-pytorch"},{"title":"lachisis/multiagent-particle-envs","url":"https://github.com/lachisis/multiagent-particle-envs"},{"title":"Stippler/cow-simulator","url":"https://github.com/Stippler/cow-simulator"},{"title":"biorobotics/PRD_environments","url":"https://github.com/biorobotics/PRD_environments"},{"title":"raoshashank/Tennis-with-MADDPG","url":"https://github.com/raoshashank/Tennis-with-MADDPG"},{"title":"Steven-Ho/multiagent-particle-envs","url":"https://github.com/Steven-Ho/multiagent-particle-envs"},{"title":"sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3","url":"https://github.com/sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3"},{"title":"Ah31/maddpg_pytorch","url":"https://github.com/Ah31/maddpg_pytorch"},{"title":"karishnu/tf-agents-multi-particle-envs","url":"https://github.com/karishnu/tf-agents-multi-particle-envs"},{"title":"SihongHo/multiagent-particle-envs","url":"https://github.com/SihongHo/multiagent-particle-envs"},{"title":"wsjeon/multiagent-particle-envs-v2","url":"https://github.com/wsjeon/multiagent-particle-envs-v2"},{"title":"baicenxiao/shaping-advice","url":"https://github.com/baicenxiao/shaping-advice"},{"title":"Yutongamber/MADDPG","url":"https://github.com/Yutongamber/MADDPG"},{"title":"SintolRTOS/multi-agent_Example","url":"https://github.com/SintolRTOS/multi-agent_Example"},{"title":"Chan1998/MAAC","url":"https://github.com/Chan1998/MAAC"},{"title":"Abdelhamid-bouzid/Multi-Agent-Deep-Deterministic-Policy-Gradient","url":"https://github.com/Abdelhamid-bouzid/Multi-Agent-Deep-Deterministic-Policy-Gradient"},{"title":"debajit15kgp/multiagent-envs","url":"https://github.com/debajit15kgp/multiagent-envs"},{"title":"johannesharmse/multi_agent_RL","url":"https://github.com/johannesharmse/multi_agent_RL"},{"title":"jingdic/rgmcomm","url":"https://github.com/jingdic/rgmcomm"},{"title":"rainandwind1/Maddpg_multiagent","url":"https://github.com/rainandwind1/Maddpg_multiagent"},{"title":"kishorkuttan/Multi-Agent-Deep-Deterministic-Policy-Gradient-actor-critic-deep-reinforcement-for-capacity-manageme","url":"https://github.com/kishorkuttan/Multi-Agent-Deep-Deterministic-Policy-Gradient-actor-critic-deep-reinforcement-for-capacity-manageme"},{"title":"dtabas/multiagent-particle-envs","url":"https://github.com/dtabas/multiagent-particle-envs"},{"title":"goldbattle/snakes_mal","url":"https://github.com/goldbattle/snakes_mal"},{"title":"ksajan/DDPG-MAPE","url":"https://github.com/ksajan/DDPG-MAPE"},{"title":"rainandwind1/MERL","url":"https://github.com/rainandwind1/MERL"},{"title":"darshil333/CSE574","url":"https://github.com/darshil333/CSE574"},{"title":"rallen10/multiagent-particle-envs","url":"https://github.com/rallen10/multiagent-particle-envs"},{"title":"tkarr21/multagent-particle-envs","url":"https://github.com/tkarr21/multagent-particle-envs"},{"title":"mauricemager/multiagent-robot","url":"https://github.com/mauricemager/multiagent-robot"},{"title":"tkarr21/multiagent-particle-envs","url":"https://github.com/tkarr21/multiagent-particle-envs"},{"title":"petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity","url":"https://github.com/petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity"},{"title":"MrDaubinet/collaboration-and-competition","url":"https://github.com/MrDaubinet/collaboration-and-competition"},{"title":"LXYYY/multiagent-particle-envs","url":"https://github.com/LXYYY/multiagent-particle-envs"},{"title":"Zorrorulz/MultiAgentDDPG-Tennis","url":"https://github.com/Zorrorulz/MultiAgentDDPG-Tennis"},{"title":"biemann/Collaboration-and-Competition","url":"https://github.com/biemann/Collaboration-and-Competition"},{"title":"hepengli/multiagent-particle-envs","url":"https://github.com/hepengli/multiagent-particle-envs"},{"title":"jiayu-ch15/MPE-for-curriculum-learning","url":"https://github.com/jiayu-ch15/MPE-for-curriculum-learning"},{"title":"marwanihab/RL_Testing_Noise_ASRN","url":"https://github.com/marwanihab/RL_Testing_Noise_ASRN"},{"title":"AleXander-Tsui/MPE","url":"https://github.com/AleXander-Tsui/MPE"},{"title":"madhur-tandon/RL-Project","url":"https://github.com/madhur-tandon/RL-Project"},{"title":"rainandwind1/MADDPG-reconstruct","url":"https://github.com/rainandwind1/MADDPG-reconstruct"},{"title":"RL-WFU/multi_agent_attack","url":"https://github.com/RL-WFU/multi_agent_attack"},{"title":"JinTanda/MADDPG_env","url":"https://github.com/JinTanda/MADDPG_env"},{"title":"jansenkeith501/CS295-MADDPG","url":"https://github.com/jansenkeith501/CS295-MADDPG"},{"title":"baradist/multiagent-particle-envs","url":"https://github.com/baradist/multiagent-particle-envs"},{"title":"krasing/DRLearningCollaboration","url":"https://github.com/krasing/DRLearningCollaboration"}],"metrics_order":"[\"Median Win Rate\"]","area":"Playing Games","uses_additional_data":0,"source":"archive","tags":[]}]}