MDP Planning under Reward Misspecification on Maze
244.2914Time (msecs)IRD
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| IRDGrid size=(9,9)2024.04 | 244.2914 | — | — | — | |
| IRDGrid size=(7,7)2024.04 | 1,061.6 | — | — | — | |
| Expectation AlignmentGrid size=(5,5)2024.04 | — | — | 131 | — | |
| Expectation AlignmentGrid size=(7,7)2024.04 | — | — | 300.5 | — | |
| IRDGrid size=(3,3)2024.04 | — | — | — | 10.87 |