Reward Adaptation on Disabled-Ant (meta-test)
331.17Average ReturnExpert
Evaluation Results
| Method | Links | |
|---|---|---|
| ExpertType=Oracle/Ground Truth2019.09 | 331.17 | |
| PEMIRLTask Mode=Reward Adaptation2019.09 | 152.62 | |
| Meta-InfoGAILTask Mode=Reward Adaptation2019.09 | -38.73 | |
| AIRLTask Mode=Reward Adaptation2019.09 | -76.21 |