Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Continual Reinforcement Learning on Atari (Default Task Order)
Loading...
0.194
Forgetting
TES-SAC
0.15308
0.42929
0.7055
0.98171
Mar 12, 2026
Forgetting
FT Score
Accuracy Score
Minimum Accuracy Score
Worst Case Accuracy Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Forgetting
FT Score
Accuracy Score
Minimum Accuracy Score
Worst Case Accuracy Score
TES-SAC
Task Order=Default
2026.03
0.194
-0.901
-0.008
-0.183
-0.143
ARROW
Task Order=Default
2026.03
0.197
-0.157
0.659
0.712
0.615
DV3
Task Order=Default
2026.03
1.217
0.046
-0.017
-0.324
-0.169
Feedback
Search any
task
Search any
task
