List your company
ResearchFormerly WizWand

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

5,646Average ScoreMAT
-231.22721,294.59142,820.414,346.2286May 30, 2022
Updated 8mo ago

Evaluation results

MethodLinks
MAT#examples=10%, pre-training status=Pre-trained2022.055,64679
MAT#examples=5%, pre-training status=Pre-trained2022.054,691235
MAPPO#examples=10%2022.053,304129
MAPPO#examples=5%2022.053,221119
MAPPO#examples=1%2022.053,017135
MAPPO#examples=0%2022.052,936301
MAT#examples=1%, pre-training status=Pre-trained2022.052,83795
MAT#examples=0%, pre-training status=Pre-trained2022.052,10089
MAT-from scratch#examples=10%, pre-training status=From scratch2022.051,6351,184
MAT-from scratch#examples=5%, pre-training status=From scratch2022.056701,098
MAT-from scratch#examples=0%, pre-training status=From scratch2022.05-0.440.4
MAT-from scratch#examples=1%, pre-training status=From scratch2022.05-5.1811