Reinforcement Learning on Procgen Maze
5.1ReturnNSER
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| NSERAlgorithm=C512026.05 | 5.1 | 4.33 | 1 | 1 | 1.35 | |
| NSERAlgorithm=DQN2026.05 | 5 | 4.62 | 19 | 6 | 1.43 | |
| NSERAlgorithm=QR-DQN2026.05 | 5 | 4.62 | 2 | 6 | 1.73 | |
| Uniform Experience ReplayAlgorithm=DQN2026.05 | 1.1 | 2.26 | 586 | 416 | — | |
| Uniform Experience ReplayAlgorithm=C512026.05 | 1.1 | 3.05 | 2 | 806 | — | |
| Uniform Experience ReplayAlgorithm=QR-DQN2026.05 | 0.9 | 710 | 10 | 41 | — |