Navigation on D4RL AntMaze umaze v2 (Initial vs Final Score)
137.4Initial D4RL ScoreIQL
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| IQLAlgorithm=IQL, Evaluation Interactions=200k2024.12 | 137.4 | 116.6 | |
| O2PPOAlgorithm=O2PPO, Evaluation Interactions=200k2024.12 | 133.7 | 184.3 | |
| O2SACAlgorithm=O2SAC, Evaluation Interactions=200k2024.12 | 131.2 | 148 | |
| O2TD3Algorithm=O2TD3, Evaluation Interactions=200k2024.12 | 128.6 | 142 | |
| Cal-QLAlgorithm=Cal-QL, Evaluation Interactions=200k2024.12 | 104.6 | 168.2 | |
| PEXAlgorithm=PEX, Evaluation Interactions=200k2024.12 | 97.6 | 112.2 | |
| O2TD3Algorithm=O2TD3, Evaluation Interactions=200k2024.12 | 92.8 | 95.8 | |
| O2SACAlgorithm=O2SAC, Evaluation Interactions=200k2024.12 | 92.8 | 93.6 | |
| PEXAlgorithm=PEX, Evaluation Interactions=200k2024.12 | 85 | 96.2 | |
| IQLAlgorithm=IQL, Evaluation Interactions=200k2024.12 | 80.8 | 80.8 | |
| Cal-QLAlgorithm=Cal-QL, Evaluation Interactions=200k2024.12 | 80.8 | 97 | |
| O2PPOAlgorithm=O2PPO, Evaluation Interactions=200k2024.12 | 77.3 | 98 |