Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Reinforcement Learning on Atari 2600 FREEWAY
Loading...
32.4
Score
DQN
8.9896
15.0673
21.145
27.2227
Jul 31, 2018
Mar 24, 2019
Nov 15, 2019
Jul 8, 2020
Mar 1, 2021
Oct 23, 2021
Jun 16, 2022
Score
Standard Deviation
Updated 4d ago
Evaluation Results
Method
Method
Links
Score
Standard Deviation
DQN
Training frames=100 mi...
2018.07
32.4
0.3
Average Human
Pure-exploration regim...
2022.06
29.6
-
DQN MMC
Training frames=100 mi...
2018.07
29.5
0.1
DQN MMC PIXELCNN
Training frames=100 mi...
2018.07
29.4
-
DQN MMC + SR
Training frames=100 mi...
2018.07
29.4
0.1
DQN MMC CTS
Training frames=100 mi...
2018.07
29.2
-
ICM
Pure-exploration regim...
2022.06
15.74
-
BYOL-Explore
Pure-exploration regim...
2022.06
12.94
-
RND
Pure-exploration regim...
2022.06
9.89
-
Feedback
Search any
task
Search any
task