Reinforcement Learning on MinAtar Asterix (test)
19.45Mean Episodic RewardEEDQN
Evaluation results
| Method | Links | ||
|---|---|---|---|
| EEDQNevaluation_window=last 100 training episodes, seeds=102025.06 | 19.45 | — | |
| AvgDQNevaluation_window=last 100 training episodes, seeds=102025.06 | 17.73 | 0.21 | |
| ESDQNevaluation_window=last 100 training episodes, seeds=102025.06 | 13.69 | 0.01 | |
| DQNevaluation_window=last 100 training episodes, seeds=102025.06 | 4.76 | 0.01 | |
| MaxMinDQNevaluation_window=last 100 training episodes, seeds=102025.06 | 3.18 | 0.01 | |
| DDQNevaluation_window=last 100 training episodes, seeds=102025.06 | 1.95 | 0.01 |