Goto on BabyAI
0.606Average Pass RatePolychromic PPO
Evaluation Results
| Method | Links | |
|---|---|---|
| Polychromic PPOevaluation_protocol=pass@1, initial-state perturbations=large2025.09 | 0.606 | |
| Poly-PPO w/ UCBevaluation_protocol=pass@1, initial-state perturbations=large2025.09 | 0.543 | |
| REINFORCE w/ Baselineevaluation_protocol=pass@1, initial-state perturbations=large2025.09 | 0.413 | |
| REINFORCE w/ UCBevaluation_protocol=pass@1, initial-state perturbations=large2025.09 | 0.371 | |
| Pretrained policyevaluation_protocol=pass@1, initial-state perturbations=large2025.09 | 0.302 | |
| PPOevaluation_protocol=pass@1, initial-state perturbations=large2025.09 | 0.211 | |
| PPO w/ UCBevaluation_protocol=pass@1, initial-state perturbations=large2025.09 | 0.184 |