List your company
ResearchFormerly WizWand

Reinforcement Learning on Atari 2600 Gravitar ALE (test)

6,712ScoreSND-VIC
-20.961,727.023,4755,222.98Mar 3, 2017Mar 1, 2018Feb 28, 2019Feb 27, 2020Feb 24, 2021Feb 23, 2022Feb 22, 2023
Updated 8mo ago

Evaluation results

MethodLinks
SND-VIC2023.026,712
RND2023.025,600
SND-STD2023.024,643
RND2018.103,906
PPO2018.103,426
Dynamics2018.103,371
Avg. Human2018.103,351
A2C+SILSelf-Imitation Learning=true2018.062,722
Baseline2023.022,611
SND-V2023.022,469
SOTAcitation=[1]2018.102,209
Reactor-PixelCNNExploration=PixelCNN2018.061,600
DQN-PixelCNNTraining frames=150M, Seeds=32017.03859.1
DQN-CTSTraining frames=150M, Seeds=32017.03498.3
TRPO-AE-SimHashExploration=SimHash2018.06482
DQNTraining frames=150M, Seeds=32017.03473
A3C-CTSExploration=CTS2018.06239
A3C-CTSTraining frames=150M, Seeds=32017.03238.68
Prior. DuelTraining frames=150M, Seeds=32017.03238