Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reinforcement Learning on Tabular CMDP (last 1,000 episodes)
Loading...
0.999
Return
Unconstrained
-0.03944
0.230155
0.49975
0.769345
Apr 5, 2026
Return
π(hack)
Updated 12d ago
Evaluation Results
Method
Method
Links
Return
π(hack)
Unconstrained
2026.04
0.999
99.9
MC-CPO
2026.04
0.6
0.04
Post-hoc
2026.04
0.0005
99.9
Feedback
Search any
task
Search any
task