List your company
ResearchFormerly WizWand

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

7,176Average ReturnMAT
-291.1481,647.43853,586.0255,524.6115May 30, 2022
Updated 8mo ago

Evaluation results

MethodLinks
MAT#examples=10%, pre-training status=Pre-trained2022.057,17674
MAT#examples=5%, pre-training status=Pre-trained2022.056,077209
MAT#examples=1%, pre-training status=Pre-trained2022.054,143230
MAT#examples=0%, pre-training status=Pre-trained2022.054,005316
MAPPO#examples=10%2022.052,955127
MAPPO#examples=5%2022.052,796137
MAPPO#examples=1%2022.052,542108
MAPPO#examples=0%2022.052,40632
MAT-from scratch#examples=10%, pre-training status=From scratch2022.051,2521,123
MAT-from scratch#examples=5%, pre-training status=From scratch2022.05743537
MAT-from scratch#examples=0%, pre-training status=From scratch2022.05-0.310.1
MAT-from scratch#examples=1%, pre-training status=From scratch2022.05-3.9517