Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Continual Reinforcement Learning on CoinRun Two-cycle (train)
Loading...
0.521
C1 Final Score
DV3
-0.13628
0.03436
0.205
0.37564
Mar 12, 2026
C1 Final Score
C2 Final Score
Max Final Score
C1 Forward Transfer
C2 Forward Transfer
Recovery Score
Accuracy Score
Min Accuracy Score
WC Accuracy Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
C1 Final Score
C2 Final Score
Max Final Score
C1 Forward Transfer
C2 Forward Transfer
Recovery Score
Accuracy Score
Min Accuracy Score
WC Accuracy Score
DV3
Task Order=Two-cycle
2026.03
0.521
0.528
0.233
0.401
0.638
1.159
0.633
-0.117
0.071
TES-SAC
Task Order=Two-cycle
2026.03
0.022
-0.039
-0.026
-0.027
0.15
1.09
0.883
0.482
0.6
ARROW
Task Order=Two-cycle
2026.03
-0.111
0.099
-0.089
0.401
0.717
1.184
1.331
0.933
0.912
Feedback
Search any
task
Search any
task