Reinforcement Learning on Hopper stand
967.865Average Episodic ReturnDreamSAC
Evaluation Results
| Method | Links | |
|---|---|---|
| DreamSACTraining Protocol=pre-training and fine-tuning, Number of Seeds=52026.03 | 967.865 | |
| DreamerV3+RNDTraining Protocol=pre-training and fine-tuning, Number of Seeds=52026.03 | 937.651 | |
| DreamerV3+PolicyTraining Protocol=trained from scratch, Number of Seeds=52026.03 | 929.851 | |
| DiSPO2024.03 | 800 | |
| MOPO2024.03 | 800 | |
| USFA2024.03 | 685 | |
| FB2024.03 | 670 | |
| COMBO2024.03 | 600 | |
| RaMP2024.03 | 255 |