Reinforcement Learning on FrozenLake v1
0.37ReturnNSER
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| NSERAlgorithm=C512026.05 | 0.37 | 203 | 1 | 1 | 1.37 | |
| NSERAlgorithm=DQN2026.05 | 0.11 | 131 | 0.03 | 1.5 | 1.55 | |
| NSERAlgorithm=QR-DQN2026.05 | 0.08 | 98 | 1 | 3.5 | 1.03 | |
| Uniform Experience ReplayAlgorithm=QR-DQN2026.05 | 0.06 | 86 | 8 | 4 | — | |
| Uniform Experience ReplayAlgorithm=DQN2026.05 | 0.04 | 56 | 1.7 | 19 | — | |
| Uniform Experience ReplayAlgorithm=C512026.05 | 0.04 | 8 | 2 | 3 | — |