Reinforcement Learning on Gridworld (Sample Complexity < 0.4 Regret)
33Sample ComplexityTRAVEL (gener. model)
Evaluation results
| Method | Links | |
|---|---|---|
| TRAVEL (gener. model)NE=12022.07 | 33 | |
| Uniform sampling (gener. model)NE=12022.07 | 43 | |
| Random ExplorationNE=12022.07 | 45 | |
| AceIRL GreedyNE=12022.07 | 46 | |
| AceIRL (Full)NE=12022.07 | 48 |