Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety-Constrained Reinforcement Learning on Extended Chain CMDP (last 1,000 episodes)
Loading...
0.069
Jc2 Constraint Metric
Unconstrained
-0.07328
0.88711
1.8475
2.80789
Apr 5, 2026
Jc2 Constraint Metric
Jc4 Constraint Metric
Updated 12d ago
Evaluation Results
Method
Method
Links
Jc2 Constraint Metric
Jc4 Constraint Metric
Unconstrained
Backbone=PPO
2026.04
0.069
4.637
MC-CPO
Backbone=PPO
2026.04
1.098
2.592
Post-hoc
Backbone=PPO
2026.04
3.626
3.626
Feedback
Search any
task
Search any
task