Single-agent Reinforcement Learning (SARL) on Seaquest Clean
1,684.1Average Episode ReturnBIRD
Evaluation Results
| Method | Links | |
|---|---|---|
| BIRD2026.05 | 1,684.1 | |
| BehaviorGuard2026.05 | 1,672.8 | |
| Original2026.05 | 1,662.8 | |
| PD2026.05 | 901.5 |
| Method | Links | |
|---|---|---|
| BIRD2026.05 | 1,684.1 | |
| BehaviorGuard2026.05 | 1,672.8 | |
| Original2026.05 | 1,662.8 | |
| PD2026.05 | 901.5 |