List your company
ResearchFormerly WizWand

Multi-Agent Reinforcement Learning on Multi-Agent MuJoCo HalfCheetah fore foot

6,054Average Evaluation ScoreMAT
-244.51,390.68753,025.8754,661.0625May 30, 2022
Updated 8mo ago

Evaluation results

MethodLinks
MAT#examples=10%, pre-training status=Pre-trained2022.056,054172
MAT#examples=5%, pre-training status=Pre-trained2022.054,856146
MAT-from scratch#examples=10%, pre-training status=From scratch2022.052,877106
MAPPO#examples=10%2022.052,480239
MAPPO#examples=5%2022.052,025371
MAT#examples=1%, pre-training status=Pre-trained2022.051,955232
MAT-from scratch#examples=5%, pre-training status=From scratch2022.051,821157
MAT#examples=0%, pre-training status=Pre-trained2022.051,313512
MAPPO#examples=1%2022.05970185
MAPPO#examples=0%2022.0562344
MAT-from scratch#examples=0%, pre-training status=From scratch2022.05-0.370.2
MAT-from scratch#examples=1%, pre-training status=From scratch2022.05-2.257.9