Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Joint action and signal payoff optimization on HybridCoop+AllD Headline discriminative cell
Loading...
2.225
Per-interaction Payoff
Reciprocity Gradient
1.5126
1.69755
1.8825
2.06745
May 8, 2026
Per-interaction Payoff
% of Reference
Discrimination Seeds Achieved
Updated 22d ago
Evaluation Results
Method
Method
Links
Per-interaction Payoff
% of Reference
Discrimination Seeds Achieved
Reciprocity Gradient
Touter=200, Seeds=20
2026.05
2.225
99
20
DPG
Touter=125, Seeds=10
2026.05
1.81
80
-
DDPG
Touter=125, Seeds=10
2026.05
1.55
69
-
TD3
Touter=125, Seeds=10
2026.05
1.54
69
-
Feedback
Search any
task
Search any
task