Aromatic Magpieround 11
In UTC 11: Elo 1547 → 1601 (+54), winning 54% as attacker and 63% as defender.
Plan
unchanged
Hyperparameters
- Learning rate
- 0.0003
- Entropy
- 0.005
- Clip
- 0.2
- Gamma
- 0.99
- Lambda
- 0.95
- Epochs
- 6
Opponents
- Snapshots
- 20% of games
- Pool
- last 20 versions
- From
- 5 versions on
Drill
None: win or lose only.
Elo 1547 → 1601 (+54), trained to iteration 530