Offline Reinforcement Learning on 70% Suboptimal Forward
51.19Final ReturnIQL + EG
Evaluation results
| Method | Links | |
|---|---|---|
| IQL + EGAlgorithm=IQL + EG, Number of seeds=52026.02 | 51.19 | |
| IQL + SELAlgorithm=IQL + SEL, Number of seeds=52026.02 | 44.59 | |
| TD3+BC + EGAlgorithm=TD3+BC + EG, Number of seeds=52026.02 | 43.41 | |
| BC + EGAlgorithm=BC + EG, Number of seeds=52026.02 | 42.99 | |
| IQL + PCGradAlgorithm=IQL + PCGrad, Number of seeds=52026.02 | 39.63 | |
| IQLAlgorithm=IQL, Number of seeds=52026.02 | 36.62 | |
| TD3+BCAlgorithm=TD3+BC, Number of seeds=52026.02 | 35.74 | |
| BCAlgorithm=BC, Number of seeds=52026.02 | 30.52 |