Continuous Control on D4RL Hopper (expert)
111.5Normalized ReturnBC(TD3+BC)
Evaluation results
| Method | Links | |
|---|---|---|
| BC(TD3+BC)Amount of data used=1 million samples, Seeds=102024.10 | 111.5 | |
| KIOAmount of data used=5k, Evaluation episodes=1002024.10 | 109.9 | |
| BC(CQL)Amount of data used=1 million samples, Seeds=32024.10 | 109 | |
| Teacher2024.10 | 108.5 | |
| IOAmount of data used=5k2024.10 | 31.8 |