Reinforcement Learning on Atari 2600 Private Eye ALE (test)
17,313ScoreSND-VIC
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SND-VIC2023.02 | 17,313 | — | |
| DQN-PixelCNNTraining frames=150M, Seeds=32017.03 | 15,806.5 | — | |
| SND-STD2023.02 | 15,089 | — | |
| RND2023.02 | 14,996 | — | |
| Baseline2023.02 | 14,870 | — | |
| DQN MMC PIXELCNNTraining frames=100 million, Sticky actions (s)=0.25, Frame skip=52018.07 | 14,386 | — | |
| A2C+SILSelf-Imitation Learning=true2018.06 | 8,684 | — | |
| DQN-CTSTraining frames=150M, Seeds=32017.03 | 8,358.7 | — | |
| SND-V2023.02 | 4,438 | — | |
| DQNTraining frames=100 million, Sticky actions (s)=0.25, Frame skip=52018.07 | 1,447.4 | 2,567.9 | |
| Prior. DuelTraining frames=150M, Seeds=32017.03 | 206 | — | |
| Reactor-PixelCNNExploration=PixelCNN2018.06 | 200 | — | |
| DQNTraining frames=150M, Seeds=32017.03 | 146.7 | — | |
| DQN MMCTraining frames=100 million, Sticky actions (s)=0.25, Frame skip=52018.07 | 113.4 | 42.3 | |
| DQN MMC + SRTraining frames=100 million, Sticky actions (s)=0.25, Frame skip=52018.07 | 104.4 | 50.4 | |
| A3C-CTSTraining frames=150M, Seeds=32017.03 | 99.32 | — | |
| A3C-CTSExploration=CTS2018.06 | 99 | — | |
| RNDTraining frames=100 million, Sticky actions (s)=0.25, Frame skip=52018.07 | 61.3 | 53.7 | |
| DQN MMC CTSTraining frames=100 million, Sticky actions (s)=0.25, Frame skip=52018.07 | 32.8 | — |