Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Expected Runtime Optimization on OneMax n=50 (test)
Loading...
4.928
ERT
pi_opt
4.90376
5.06738
5.231
5.39462
Dec 3, 2025
ERT
Updated 5mo ago
Evaluation Results
Method
Method
Links
ERT
pi_opt
Policy Type=Optimal
2025.12
4.928
DDQN
Reward=Scaled
2025.12
5.105
DDQN
Reward=Naïve
2025.12
5.428
pi_cont
Policy Type=theory-der...
2025.12
5.448
pi_disc
Policy Type=theory-der...
2025.12
5.48
PPO
Reward=Scaled
2025.12
5.526
PPO
Reward=Naïve
2025.12
5.534
Feedback
Search any
task
Search any
task
