Reinforcement Learning on MinAtar Breakout (test)
25.77Mean Episodic RewardEEDQN
Evaluation results
| Method | Links | ||
|---|---|---|---|
| EEDQNevaluation_window=last 100 training episodes, seeds=102025.06 | 25.77 | — | |
| ESDQNevaluation_window=last 100 training episodes, seeds=102025.06 | 23.86 | 0.26 | |
| AvgDQNevaluation_window=last 100 training episodes, seeds=102025.06 | 19.54 | 0.01 | |
| DQNevaluation_window=last 100 training episodes, seeds=102025.06 | 13.81 | 0.01 | |
| MaxMinDQNevaluation_window=last 100 training episodes, seeds=102025.06 | 13.54 | 0.01 | |
| DDQNevaluation_window=last 100 training episodes, seeds=102025.06 | 10.35 | 0.01 |