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

Safe Offline Multi-Agent Reinforcement Learning research benchmarks · SOTA2 Research

Safe Offline Multi-Agent Reinforcement Learning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

simple spread random

CBFs-Guided Diffusion Model

0.56Reward

3

Jun 12, 2026

simple spread medium

CBFs-Guided Diffusion Model

0.88Reward

3

Jun 12, 2026

simple spread md

CBFs-Guided Diffusion Model

82Reward

3

Jun 12, 2026

simple spread expert

1.35Reward

3

Jun 12, 2026

2halfcheetah poor

CBFs-Guided Diffusion Model

0.13Reward

3

Jun 12, 2026

2halfcheetah medium

0.51Reward

3

Jun 12, 2026

2halfcheetah good

1.11Reward (2halfcheetah)

3

Jun 12, 2026

CBFs-Guided Diffusion Model

0.4Reward

3

Jun 12, 2026

0.69Reward

3

Jun 12, 2026

CBFs-Guided Diffusion Model

0.99Reward

3

Jun 12, 2026

CBFs-Guided Diffusion Model

0.33Reward

3

Jun 12, 2026

CBFs-Guided Diffusion Model

0.6Reward

3

Jun 12, 2026

CBFs-Guided Diffusion Model

1.05Reward

3

Jun 12, 2026

Popular datasets

Simple-Spread 2ant 4ant 2halfcheetah halfcheetah

Follow for updates

Join SOTA2 Contact