Reinforcement Learning on Atari 2600 Enduro
1,473Mean ScoreRainbow
Evaluation results
| Method | Links | ||
|---|---|---|---|
| RainbowPlasticity=full, Activation=rational2021.02 | 1,473 | 1,973 | |
| RainbowPlasticity=regularised, Activation=joint-rational2021.02 | 1,470 | 1,964 | |
| RainbowPlasticity=rigid, Activation=Leaky ReLU2021.02 | 844 | 1,388 | |
| MTSpark_ADD# Trainable Parameters=3,300,3572025.04 | 371.2 | — | |
| Human2025.04 | 368 | — | |
| DSQN# Trainable Parameters=1,693,6822025.04 | 362.2 | — | |
| DSQN_D# Trainable Parameters=3,300,3392025.04 | 356 | — | |
| SwitchMT# Trainable Parameters=3,300,3572025.04 | 355.2 | — | |
| DQN# Trainable Parameters=1,693,6822025.04 | 0 | — | |
| DQN_D# Trainable Parameters=3,300,3392025.04 | 0 | — |