Reinforcement Learning on Walker-Bodyparts Start OpenAI Gym Mujoco (initialization)
222.88Average RewardVBLRL
Evaluation results
| Method | Links | |
|---|---|---|
| VBLRLsamples per iteration=1x2022.10 | 222.88 | |
| T-HiP-MDPsamples per iteration=1x2022.10 | 173.33 | |
| LPG-FTWsamples per iteration=2x2022.10 | 164.79 | |
| EWCsamples per iteration=2x2022.10 | 164 | |
| Single-task MBRLmode=train from scratch2022.10 | 4.64 |