Offline Reinforcement Learning on Expert Forward
63.52Final ReturnIQL + EG
Evaluation results
| Method | Links | |
|---|---|---|
| IQL + EGAlgorithm=IQL + EG, Number of seeds=52026.02 | 63.52 | |
| BC + EGAlgorithm=BC + EG, Number of seeds=52026.02 | 63.47 | |
| IQLAlgorithm=IQL, Number of seeds=52026.02 | 63.39 | |
| IQL + SELAlgorithm=IQL + SEL, Number of seeds=52026.02 | 63.37 | |
| IQL + PCGradAlgorithm=IQL + PCGrad, Number of seeds=52026.02 | 63.37 | |
| BCAlgorithm=BC, Number of seeds=52026.02 | 63.31 | |
| TD3+BC + EGAlgorithm=TD3+BC + EG, Number of seeds=52026.02 | 59.34 | |
| TD3+BCAlgorithm=TD3+BC, Number of seeds=52026.02 | 52.14 |