Instruction Following on BabyAI Goto
0.575Average Episodic Reward
Poly-PPO
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.09 | 0.575 | 80.2 | |
2025.09 | 0.561 | 76.2 | |
2025.09 | 0.538 | 73.4 | |
2025.09 | 0.533 | 73 | |
2025.09 | 0.428 | 47.4 | |
2025.09 | 0.406 | 46.2 | |
2025.09 | 0.246 | 34.2 |