Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Offline Actor-Critic Optimization on Gymnasium LunarLander
Loading...
-25.726
Actor Loss
MA-SOBA
-26.523
-21.14325
-15.7635
-10.38375
Jun 21, 2026
Actor Loss
Stability (Std)
Spike (Max Jump)
Gradient Norm
Updated 1mo ago
Evaluation Results
Method
Method
Links
Actor Loss
Stability (Std)
Spike (Max Jump)
Gradient Norm
MA-SOBA
Seeds=5
2026.06
-25.726
0.004
0.459
0.621
RQ-TTSA
Seeds=5
2026.06
-25.721
0.003
0.457
0.464
TTSA
Seeds=5
2026.06
-25.661
0.006
0.43
0.383
ψ-Variant
Seeds=5
2026.06
-25.619
0.007
0.247
0.649
AccBO
Seeds=5
2026.06
-12.863
1.089
0.081
1.55
BiSLS
Seeds=5
2026.06
-5.801
0.434
0.032
1.781
Feedback
Search any
task
Search any
task