Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Ant on MuJoCo (eval)
Loading...
3,313.1
Reward
PPO-Lagrangian
2,177.004
2,471.952
2,766.9
3,061.848
Apr 17, 2025
Reward
Cost
Labeled Trajectories
Updated 25d ago
Evaluation Results
Method
Method
Links
Reward
Cost
Labeled Trajectories
PPO-Lagrangian
Knowledge Level=Oracle
2025.04
3,313.1
14.4
-
CPPO-PID
Knowledge Level=Oracle
2025.04
3,284.7
12.8
-
C-T Baseline
Knowledge Level=Zero K...
2025.04
3,096.7
20.3
6,000
TraCeS
Knowledge Level=Zero K...
2025.04
2,885.4
19.5
4,657
RLSF
Knowledge Level=Partia...
2025.04
2,220.7
5.8
9,036
Feedback
Search any
task
Search any
task