Reinforcement Learning on MinAtar Freeway (test)
41.3Mean Episodic RewardEEDQN
Evaluation results
| Method | Links | ||
|---|---|---|---|
| EEDQNevaluation_window=last 100 training episodes, seeds=102025.06 | 41.3 | — | |
| MaxMinDQNevaluation_window=last 100 training episodes, seeds=102025.06 | 39.1 | 0.05 | |
| AvgDQNevaluation_window=last 100 training episodes, seeds=102025.06 | 28.6 | 0.01 | |
| ESDQNevaluation_window=last 100 training episodes, seeds=102025.06 | 28.26 | 0.03 | |
| DQNevaluation_window=last 100 training episodes, seeds=102025.06 | 20.03 | 0.04 | |
| DDQNevaluation_window=last 100 training episodes, seeds=102025.06 | 14.14 | 0.05 |