Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

MaMuJoCo dataset and benchmarks · SOTA2 Research

Research Datasets

MaMuJoCo

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Multi-Agent Reinforcement Learning

MAMuJoCo HalfCheetah Extreme Env v2 (various)

2,757.2Average Return

24

Multi-Agent Reinforcement Learning

MAMuJoCo HalfCheetah Random Env v2 (various)

3,178.7Average Return

24

Multi-agent Continual Cooperation

MAMuJoCo Reward (Expert)

36.48Forward Transfer

14

Multi-Agent Reinforcement Learning

MAMuJoCo Walker2d 6x1 (test)

1,116.75Average Episodic Return

13

Multi-agent Reinforcement Learning

MaMuJoCo OMIGA 2-Ant (Medium)

1,798.05Average Episode Reward

11

Multi-agent Reinforcement Learning

MaMuJoCo OMIGA 2-Ant (Medium-Replay)

1,822.72Average Episode Reward

11

Multi-agent Reinforcement Learning

MaMuJoCo OMIGA 2-Ant (Medium-Expert)

2,002Average Episode Reward

11

Multi-agent Reinforcement Learning

MaMuJoCo OMIGA 3-Hopper (Medium)

3,360Average Episode Reward

11

Multi-agent Reinforcement Learning

MaMuJoCo (OMIGA) 6-HalfCheetah Medium

4,695Average Episode Reward

11

Multi-agent Reinforcement Learning

MaMuJoCo OMIGA 6-HalfCheetah (Medium-Replay)

4,582Avg Episode Reward

11

Multi-agent Reinforcement Learning

MaMuJoCo OMIGA 6-HalfCheetah (Medium-Expert)

5,237Average Episode Reward

11

Multi-agent Reinforcement Learning

MaMuJoCo OMIGA 6-HalfCheetah (Expert)

5,545Average Episode Reward

11

Multi-Agent Offline Reinforcement Learning

MaMuJoCo 2HalfCheetah Medium

4,554.11Performance

9

Dynamics task stream

MAMuJoCo Medium

2.97Backward Transfer

8

Dynamics task stream

MAMuJoCo (Expert)

11.32Backward Transfer

8

Reward task stream

MAMuJoCo Medium

16.13Backward Transfer

8

Reward task stream

MAMuJoCo (Expert)

21.57Backward Transfer

8

Multi-Agent Reinforcement Learning

MAMuJoCo Ant 8x1 (test)

45.06Average Episodic Return

8

Multi-Agent Reinforcement Learning

MAMuJoCo Hopper 3x1 (test)

31.02Average Episodic Return

8

Multi-Agent Reinforcement Learning

MAMuJoCo HalfCheetah 6x1 (test)

43.1Average Episodic Return

8

Multi-agent continuous control

MaMuJoCo HalfCheetah Expert v2

118.5Score

8

Multi-agent continuous control

MaMuJoCo HalfCheetah v2 (Med-rep)

59.5Score

8

Multi-agent continuous control

MaMuJoCo HalfCheetah v2 (Random)

39.7Score

8

Multi-agent Continual Cooperation

MAMuJoCo Dynamics Medium

1.26Forward Transfer

7

Multi-agent Continual Cooperation

MAMuJoCo Reward Medium

27.15Forward Transfer

7

Page 1 of 2

PreviousNext

Popular tasks

Multi-Agent Reinforcement Learning Offline Multi-Agent Reinforcement Learning Multi-agent Offline Reinforcement Learning Multi-agent continuous control 2-Ant

Follow for updates

Join SOTA2 Contact