Reinforcement Learning on Hopper-Gravity OpenAI Gym Mujoco (train)
352.1Average RewardLPG-FTW
Evaluation results
| Method | Links | |
|---|---|---|
| LPG-FTWsamples per iteration=2x2022.10 | 352.1 | |
| EWCsamples per iteration=2x2022.10 | 345.47 | |
| VBLRLsamples per iteration=1x2022.10 | 332.89 | |
| T-HiP-MDPsamples per iteration=1x2022.10 | 285.87 | |
| Single-task MBRLmode=train from scratch2022.10 | 20.46 |