Reinforcement Learning on Random MDPs
21Sample Complexity (Regret < 0.4)AceIRL (Full)
Evaluation results
| Method | Links | |
|---|---|---|
| AceIRL (Full)NE=12022.07 | 21 | |
| Uniform sampling (gener. model)NE=12022.07 | 22 | |
| Random ExplorationNE=12022.07 | 22 | |
| AceIRL GreedyNE=12022.07 | 23 | |
| TRAVEL (gener. model)NE=12022.07 | 27 |