Multi-agent Reinforcement Learning on Dectiger
37.72RewardOurs
Evaluation results
| Method | Links | |
|---|---|---|
| OursHorizon=72023.08 | 37.72 | |
| OursHorizon=62023.08 | 36.03 | |
| OursHorizon=52023.08 | 27.95 | |
| OursHorizon=42023.08 | 20.89 | |
| OursHorizon=32023.08 | 13.06 | |
| FM-EHorizon=42023.08 | -4.76 | |
| FM-EHorizon=32023.08 | -6 | |
| RNN-EHorizon=32023.08 | -6 | |
| FM-EHorizon=52023.08 | -6.37 | |
| RNN-EHorizon=42023.08 | -7 | |
| FM-EHorizon=62023.08 | -7.99 | |
| FM-EHorizon=72023.08 | -7.99 | |
| RNN-EHorizon=52023.08 | -10.04 | |
| RNN-EHorizon=62023.08 | -11.9 | |
| RNN-EHorizon=72023.08 | -13.92 |