POMDP Simulation on Tag
1.7RewardPerfect
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Perfect2022.09 | 1.7 | — | |
| Naivev=12022.09 | -1.6 | 3.7 | |
| Scaled Agenttau=0.992022.09 | -1.8 | 3.1 | |
| Noisy Agentlambda=52022.09 | -1.8 | 3.2 | |
| Noisy Agentlambda=22022.09 | -2 | 3.3 | |
| Scaled Agenttau=0.752022.09 | -2.4 | 3.3 | |
| Noisy Agentlambda=12022.09 | -2.4 | 3.6 | |
| Scaled Agenttau=0.52022.09 | -3.6 | 3.9 | |
| Naivev=0.752022.09 | -3.8 | 6.1 | |
| Naivev=0.52022.09 | -6.8 | 15.2 | |
| Normal2022.09 | -10.7 | — |