Offline Reinforcement Learning on D4RL Gym walker2d medium-expert
121.2Normalized Average Return
RORL
Updated 4d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2022.06 | 121.2 | |
2024.01 | 118.2 | |
2021.10 | 116.7 | |
2022.06 | 116.7 | |
2024.01 | 116.7 | |
2022.06 | 115.4 | |
2021.10 | 114.7 | |
2022.06 | 114.7 | |
2024.01 | 114.7 | |
2021.10 | 110.1 | |
2022.06 | 110.1 | |
2021.10 | 109.1 | |
2022.06 | 109.1 | |
2021.06 | 108.8 | |
2021.06 | 108.1 | |
2021.06 | 101.9 | |
2024.01 | 98.7 | |
2021.06 | 91 | |
2021.10 | 90.1 | |
2022.06 | 90.1 | |
2024.01 | 90.1 | |
2021.06 | 81.6 | |
2021.06 | 70.2 | |
2021.10 | 68.8 | |
2021.10 | 55.2 | |
2021.06 | 36.6 | |
2021.10 | 27.9 | |
2021.10 | 16 | |
2021.10 | 1.5 | |
2021.10 | 1.3 | |
2021.10 | -0.2 |