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

MPE World dataset and benchmarks · SOTA2 Research

Research Datasets

MPE World

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Multi-agent Offline Reinforcement Learning

MPE World Expert

135.2Score

16

Multi-agent Reinforcement Learning

MPE World v1 (Expert)

119.7Normalized Score

10

Multi-Agent Reinforcement Learning

MPE World Medium Replay

65.9Mean Episode Return

8

Offline Multi-Agent Reinforcement Learning

MPE World (Medium)

104.9Average Normalized Score

8

Multi-agent Offline Reinforcement Learning

MPE World Medium

0.938Score

8

Multi-agent Offline Reinforcement Learning

MPE World (Medium-replay)

73.4Score

8

Multi-agent Offline Reinforcement Learning

MPE World (Random)

68Score

8

Multi-Agent Reinforcement Learning

MPE World Medium Expert

89.4Normalized Score

4

Multi-Agent Reinforcement Learning

MPE World Medium

84.5Normalized Score

4

Multi-Agent Reinforcement Learning

MPE World Random Medium

42.7Normalized Score

4

Multi-Agent Reinforcement Learning

MPE World Expert

91.8Mean Episode Return

4

Multi-Agent Reinforcement Learning

MPE World Medium Expert

79.9Mean Episode Return

4

Multi-Agent Reinforcement Learning

MPE World Medium

57.5Mean Episode Return

4

Multi-Agent Reinforcement Learning

MPE World Random Medium

30.3Mean Episode Return

4

Multi-Agent Reinforcement Learning

MPE World (Random)

35.6Mean Episode Return

4

Multi-agent Reinforcement Learning

MPE World Medium v1

0.938Normalized Score

4

Multi-agent Reinforcement Learning

MPE World v1 (Med-Rep)

73.4Normalized Score

4

Multi-agent Reinforcement Learning

MPE World v1 (Random)

68Normalized Score

4

Multi-Agent Reinforcement Learning

MPE World

40Score (Random)

3

Popular tasks

Multi-Agent Reinforcement Learning Multi-agent Offline Reinforcement Learning Offline Multi-Agent Reinforcement Learning

Follow for updates

Join SOTA2 Contact