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

Multi-agent Offline Reinforcement Learning research benchmarks · SOTA2 Research

Multi-agent Offline Reinforcement Learning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

MPE World Expert

135.2Score

16

Mar 31, 2026

MPE PP (Expert)

125.6Score

16

Mar 31, 2026

86.3Score

16

Mar 31, 2026

MPE PP (Medium-replay)

87.3Score

16

Mar 31, 2026

MPE PP (Random)

92.8Score

16

Mar 31, 2026

MPE CN (Expert)

136.4Score

16

Mar 31, 2026

MPE CN (Medium)

85.1Score

16

Mar 31, 2026

MPE CN (Medium-replay)

95.4Score

16

Mar 31, 2026

MPE CN (Random)

88.3Score

16

Mar 31, 2026

MaMuJoCo 2HalfCheetah Medium

MADDPG + BC + Diffusion

4,554.11Performance

9

May 29, 2026

MPE World Medium

0.938Score

8

Feb 26, 2026

MPE World (Medium-replay)

73.4Score

8

Mar 31, 2026

MPE World (Random)

68Score

8

Feb 26, 2026

MaMuJoCo 4Ant (Replay)

1,875.51Performance Score

3

Apr 28, 2026

MaMuJoCo 2HalfCheetah (Poor)

MADDPG + BC + Diffusion

2,713.69Return

3

Apr 28, 2026

MaMuJoCo 2HalfCheetah (Good)

7,208.19Return

3

Apr 28, 2026

MaMuJoCo 2HalfCheetah (Replay)

6,925.02Return

3

Apr 28, 2026

Popular datasets

MaMuJoCo MPE World MPE PP MPE MPE CN

Follow for updates

Join SOTA2 Contact