Find the optimal epsilon decay for decay of 1000 and 3000 epochs
Cross validation for epsilon decay
| | L0 | L1 | L2 | L3 |
|---|---|---|---|---|
| learning rate | 0.2 | 0.2 | 0.2 | 0.2 |
| | E0 |
|---|---|
| epsilon | 0.05 |
| | ED0 | ED1 | ED2 | ED3 |
|---|---|---|---|---|
| epsilon decay | none | decay-1000-80 | decay-1000-50 | decay-1000-20 |
| | ED4 | ED5 | ED6 | ED7 |
| | none | decay-3000-80 | decay-3000-50 | decay-3000-20 |
| | D0 |
|---|---|
| discount | 0.3 |
| | M0 |
|---|---|
| mapping | non-linear-3 |
| | R0 |
|---|---|
| reward handler | can-see |
| | F0 |
|---|---|
| fetch mode | eager |