Linear off-policy prediction on New two-state environment
3.89Max RMSEETD
Evaluation results
| Method | Links | ||
|---|---|---|---|
| ETDalpha=0.01, total runs=102026.05 | 3.89 | 1 | |
| GTD2alpha=0.01, total runs=102026.05 | 8.735 | 0 | |
| TETDalpha=0.01, total runs=102026.05 | 8.747 | 0 | |
| RETDalpha=0.01, total runs=102026.05 | 8.758 | 0 | |
| TDRCalpha=0.01, total runs=102026.05 | 8.79 | 0 | |
| TDCalpha=0.01, total runs=102026.05 | 8.794 | 0 | |
| TDalpha=0.01, total runs=102026.05 | 8.802 | 0 | |
| CETDalpha=0.01, total runs=102026.05 | 64.92 | 0 |