Reinforcement Learning on Cheetah-Bodyparts OpenAI Gym Mujoco (train)
173.97Average RewardVBLRL
Evaluation results
| Method | Links | |
|---|---|---|
| VBLRLsamples per iteration=1x2022.10 | 173.97 | |
| T-HiP-MDPsamples per iteration=1x2022.10 | 87.2 | |
| Single-task MBRLmode=train from scratch2022.10 | -58.93 | |
| LPG-FTWsamples per iteration=2x2022.10 | -217.86 | |
| EWCsamples per iteration=2x2022.10 | -5,454.52 |