Offline Reinforcement Learning on sawyer-door-close
100Success RateBatch Max
Evaluation Results
| Method | Links | |
|---|---|---|
| Batch Max2021.02 | 100 | |
| MOPO2021.02 | 65.8 | |
| MOREL2021.02 | 42.9 | |
| CQL2021.02 | 36.7 | |
| Batch Mean2021.02 | 5 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| Batch Max2021.02 | 100 | |
| MOPO2021.02 | 65.8 | |
| MOREL2021.02 | 42.9 | |
| CQL2021.02 | 36.7 | |
| Batch Mean2021.02 | 5 |