Offline Reinforcement Learning on ant-angle
2,660.3Average ReturnMOREL
Evaluation Results
| Method | Links | |
|---|---|---|
| MOREL2021.02 | 2,660.3 | |
| MOPO2021.02 | 2,530.9 | |
| CQL2021.02 | 2,473.4 | |
| Batch Max2021.02 | 2,311.9 | |
| Batch Mean2021.02 | 866.7 |
| Method | Links | |
|---|---|---|
| MOREL2021.02 | 2,660.3 | |
| MOPO2021.02 | 2,530.9 | |
| CQL2021.02 | 2,473.4 | |
| Batch Max2021.02 | 2,311.9 | |
| Batch Mean2021.02 | 866.7 |