Reinforcement Learning on Atari 2600 SpaceInvaders
1,400Best Stable ScoreA3C
Evaluation results
| Method | Links | ||
|---|---|---|---|
| A3C2018.01 | 1,400 | 15 | |
| HyperNeatinput type=raw pixel, # of neurons=~30342018.06 | 1,251 | — | |
| IDVQ+DRSC+XNESinput type=raw pixel, max run length=200 interactions, frameskip=5, # of neurons=62018.06 | 830 | — | |
| BA3C2018.01 | 700 | 24 | |
| OpenAI ESinput type=raw pixel, # of neurons=~6502018.06 | 678.5 | — | |
| DDRL A3C2018.01 | 650 | 0.5 | |
| GA3C2018.01 | 600 | 24 |