Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Policy Evaluation on 2x2 Queueing Network rho = (0.95, 0.85)
Loading...
1,185.4
Expected Value
Exact optimal
1,181.688
1,206.744
1,231.8
1,256.856
Jun 9, 2026
Expected Value
Standard Error
Performance Gap (%)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Expected Value
Standard Error
Performance Gap (%)
Exact optimal
c^ov=0.1
2026.06
1,185.4
2
-
BTSD-PPO
c^ov=0.1
2026.06
1,198.1
1.6
1.1
Exact optimal
c^ov=0.3
2026.06
1,218.1
2
-
BTSD-PPO
c^ov=0.3
2026.06
1,234.2
1.9
1.3
Exact optimal
c^ov=0.6
2026.06
1,264.5
2
-
BTSD-PPO
c^ov=0.6
2026.06
1,278.2
1.9
1.1
Feedback
Search any
task
Search any
task