Multi Agent Reinforcement Learning On
评估指标
final agent reward
评测结果
各个模型在此基准测试上的表现结果
模型名称 | final agent reward | Paper Title | Repository |
|---|---|---|---|
| MATD3 | -14 | Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Critics |
0 of 1 row(s) selected.
各个模型在此基准测试上的表现结果
模型名称 | final agent reward | Paper Title | Repository |
|---|---|---|---|
| MATD3 | -14 | Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Critics |