Point-Maze
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Inverse Reinforcement Learning | Point Maze | Normalized Performance1.03 | 6 | |
| Policy Generalization | Point Maze (test) | Average Return-5.21 | 6 | |
| Reward Adaptation | Point-Maze Shift (meta-test) | Average Return-5.37 | 4 | |
| Inverse Reinforcement Learning | Point Maze Flipped | Normalized Performance96 | 3 | |
| Policy Generalization | Point-Maze-Shift (meta-test) | Average Return-28.61 | 3 |
Showing 5 of 5 rows