Reinforcement Learning on MinAtar Seaquest (test)
27.58Mean Episodic RewardMaxMinDQN
Evaluation results
| Method | Links | ||
|---|---|---|---|
| MaxMinDQNevaluation_window=last 100 training episodes, seeds=102025.06 | 27.58 | 0.01 | |
| EEDQNevaluation_window=last 100 training episodes, seeds=102025.06 | 10.78 | — | |
| ESDQNevaluation_window=last 100 training episodes, seeds=102025.06 | 3.18 | 0.01 | |
| AvgDQNevaluation_window=last 100 training episodes, seeds=102025.06 | 3.01 | 0.01 | |
| DDQNevaluation_window=last 100 training episodes, seeds=102025.06 | 0.68 | 0.01 | |
| DQNevaluation_window=last 100 training episodes, seeds=102025.06 | 0.65 | 0.01 |