Reinforcement Learning on Atari 2600 Phoenix
4,600ScoreIDVQ+DRSC+XNES
Evaluation Results
| Method | Links | |
|---|---|---|
| IDVQ+DRSC+XNESinput type=raw pixel, max run length=200 interactions, frameskip=5, # of neurons=82018.06 | 4,600 | |
| OpenAI ESinput type=raw pixel, # of neurons=~6502018.06 | 4,041 | |
| HyperNeatinput type=raw pixel, # of neurons=~30342018.06 | 1,762 |