Reward Metrics on Meta-World handle-press-side
19,941,225Average Episode RewardTargeted PGD
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Targeted PGDAccess model=white-box, Adversary’s knowledge=target policy2024.06 | 19,941,225 | 4,546,721 | |
| RandomAccess model=no-box, Adversary’s knowledge=no knowledge2024.06 | 18,651,340 | 4,546,721 | |
| Rew Max (PA-AD)Access model=white-box, Adversary’s knowledge=reward function2024.06 | 4,726,175 | 4,546,721 | |
| BIA-ILfDAccess model=black-box, Adversary’s knowledge=demonstrations2024.06 | 4,631,408 | 4,546,721 | |
| BIA-ILfOAccess model=no-box, Adversary’s knowledge=demonstrations2024.06 | 4,627,586 | 4,546,721 | |
| Rew Max (SA-RL)Access model=black-box, Adversary’s knowledge=reward function2024.06 | 4,625,175 | 4,546,721 |