Offline Reinforcement Learning on Expert Backward
67.24Final ReturnIQL + SEL
Evaluation Results
| Method | Links | |
|---|---|---|
| IQL + SELAlgorithm=IQL + SEL, Number of seeds=52026.02 | 67.24 | |
| BC + EGAlgorithm=BC + EG, Number of seeds=52026.02 | 67.24 | |
| IQL + EGAlgorithm=IQL + EG, Number of seeds=52026.02 | 67.24 | |
| BCAlgorithm=BC, Number of seeds=52026.02 | 67.17 | |
| IQLAlgorithm=IQL, Number of seeds=52026.02 | 67.1 | |
| IQL + PCGradAlgorithm=IQL + PCGrad, Number of seeds=52026.02 | 67.05 | |
| IQL + EGAlgorithm=IQL + EG, Number of seeds=52026.02 | 57.58 | |
| IQL + PCGradAlgorithm=IQL + PCGrad, Number of seeds=52026.02 | 55.94 | |
| IQL + SELAlgorithm=IQL + SEL, Number of seeds=52026.02 | 55.73 | |
| TD3+BC + EGAlgorithm=TD3+BC + EG, Number of seeds=52026.02 | 55.67 | |
| TD3+BCAlgorithm=TD3+BC, Number of seeds=52026.02 | 52.31 | |
| TD3+BC + EGAlgorithm=TD3+BC + EG, Number of seeds=52026.02 | 51.98 | |
| IQLAlgorithm=IQL, Number of seeds=52026.02 | 51.86 | |
| BC + EGAlgorithm=BC + EG, Number of seeds=52026.02 | 48.64 | |
| TD3+BCAlgorithm=TD3+BC, Number of seeds=52026.02 | 47.94 | |
| BCAlgorithm=BC, Number of seeds=52026.02 | 42.87 |