Continuous Control on D4RL Halfcheetah-expert
107Normalized ReturnBC(CQL)
Evaluation results
| Method | Links | |
|---|---|---|
| BC(CQL)Amount of data used=1 million samples, Seeds=32024.10 | 107 | |
| BC(TD3+BC)Amount of data used=1 million samples, Seeds=102024.10 | 105.2 | |
| Teacher2024.10 | 88.1 | |
| KIOAmount of data used=10k, Evaluation episodes=1002024.10 | 84.4 | |
| IOAmount of data used=10k2024.10 | -1.7 |