Reinforcement Learning on Atari 2600 Frostbite ALE (test)
6,439Avg RewardA2C+SIL
Evaluation Results
| Method | Links | |
|---|---|---|
| A2C+SILSelf-Imitation Learning=true2018.06 | 6,439 | |
| TRPO-AE-SimHashExploration=SimHash2018.06 | 5,214 | |
| Reactor-PixelCNNExploration=PixelCNN2018.06 | 4,800 | |
| GA (1B)input type=raw pixel, # of neurons=~6502018.06 | 4,536 | |
| NSRA-ESinput type=Atari RAM, # of neurons=~6502018.06 | 3,785 | |
| HyperNeatinput type=raw pixel, # of neurons=~30342018.06 | 2,260 | |
| Average Human2024.05 | 2,000 | |
| DDQN2024.05 | 1,050 | |
| FDQN2024.05 | 1,015 | |
| DQN2024.05 | 1,000 | |
| OpenAI ESinput type=raw pixel, # of neurons=~6502018.06 | 370 | |
| A3C-CTSExploration=CTS2018.06 | 352 | |
| IDVQ+DRSC+XNESinput type=raw pixel, max run length=200 interactions, frameskip=5, # of neurons=182018.06 | 300 |