Finding target T_uniform on MeD
1Average SimilarityOracle
Evaluation results
| Method | Links | |
|---|---|---|
| Oraclealpha=02026.03 | 1 | |
| Oraclealpha=12026.03 | 1 | |
| Oraclealpha=0.752026.03 | 0.988 | |
| Oraclealpha=0.252026.03 | 0.978 | |
| Oraclealpha=0.52026.03 | 0.977 | |
| DQNalpha=02026.03 | 0.918 | |
| SARSAalpha=02026.03 | 0.911 | |
| A3Calpha=02026.03 | 0.91 | |
| A2Calpha=02026.03 | 0.907 | |
| A3Calpha=12026.03 | 0.899 | |
| DQNalpha=12026.03 | 0.893 | |
| A2Calpha=12026.03 | 0.886 | |
| SARSAalpha=0.252026.03 | 0.88 | |
| A3Calpha=0.252026.03 | 0.88 | |
| DQNalpha=0.252026.03 | 0.878 | |
| A2Calpha=0.252026.03 | 0.877 | |
| SARSAalpha=0.52026.03 | 0.876 | |
| DQNalpha=0.52026.03 | 0.871 | |
| SARSAalpha=0.752026.03 | 0.87 | |
| A2Calpha=0.52026.03 | 0.869 | |
| A3Calpha=0.52026.03 | 0.869 | |
| A3Calpha=0.752026.03 | 0.866 | |
| A2Calpha=0.752026.03 | 0.861 | |
| DQNalpha=0.752026.03 | 0.86 | |
| SARSAalpha=12026.03 | 0.852 |