Offline Reinforcement Learning on Expert Replay Forward
57.04Final ReturnTD3+BC + EG
Evaluation results
| Method | Links | |
|---|---|---|
| TD3+BC + EGAlgorithm=TD3+BC + EG, Number of seeds=52026.02 | 57.04 | |
| TD3+BCAlgorithm=TD3+BC, Number of seeds=52026.02 | 55.66 | |
| IQL + SELAlgorithm=IQL + SEL, Number of seeds=52026.02 | 55.01 | |
| IQL + EGAlgorithm=IQL + EG, Number of seeds=52026.02 | 54.62 | |
| IQLAlgorithm=IQL, Number of seeds=52026.02 | 54.61 | |
| IQL + PCGradAlgorithm=IQL + PCGrad, Number of seeds=52026.02 | 53.84 | |
| BC + EGAlgorithm=BC + EG, Number of seeds=52026.02 | 51.89 | |
| BCAlgorithm=BC, Number of seeds=52026.02 | 49.71 |