Reinforcement Learning on Procgen CoinRun
5.65ReturnNSER
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| NSERAlgorithm=DQN2026.05 | 5.65 | 3 | 21 | 50 | 2.64 | |
| NSERAlgorithm=QR-DQN2026.05 | 4.8 | 5.67 | 5 | 205 | 1.27 | |
| Uniform Experience ReplayAlgorithm=QR-DQN2026.05 | 3.1 | 1.77 | 7 | 282 | — | |
| NSERAlgorithm=C512026.05 | 2.5 | 6.34 | 5 | 876 | 1.08 | |
| Uniform Experience ReplayAlgorithm=C512026.05 | 2.2 | 6.13 | 30 | 980 | — | |
| Uniform Experience ReplayAlgorithm=DQN2026.05 | 1.2 | 2.83 | 36 | 532 | — |