Reinforcement Learning on Atari 2600 TimePilot
7,340ScoreHyperNeat
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| HyperNeatinput type=raw pixel, # of neurons=~30342018.06 | 7,340 | — | |
| RainbowPlasticity=regularised, Activation=joint-rational2021.02 | 6,411 | 15,900 | |
| RainbowPlasticity=full, Activation=rational2021.02 | 5,386 | 15,900 | |
| OpenAI ESinput type=raw pixel, # of neurons=~6502018.06 | 4,970 | — | |
| IDVQ+DRSC+XNESinput type=raw pixel, max run length=200 interactions, frameskip=5, # of neurons=102018.06 | 4,600 | — | |
| RainbowPlasticity=rigid, Activation=Leaky ReLU2021.02 | 3,926 | 12,700 |