Multi-agent coordination on Hanabi 5-player JaxMARL
23.73SP ScoreIPPO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| IPPOArchitecture=PP LSTM, Entropy coefficient (α)=0.08, Seeds=5, λGAE=0.92025.11 | 23.73 | 23.59 |
| Method | Links | ||
|---|---|---|---|
| IPPOArchitecture=PP LSTM, Entropy coefficient (α)=0.08, Seeds=5, λGAE=0.92025.11 | 23.73 | 23.59 |