Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Continuous Control (MuJoCo) on HalfCheetah v4
Loading...
4,850
Mean Episodic Return
FP16-PPO
3,945.2
4,180.1
4,415
4,649.9
Apr 27, 2026
Mean Episodic Return
FP16 Usage
Updated 1mo ago
Evaluation Results
Method
Method
Links
Mean Episodic Return
FP16 Usage
FP16-PPO
Precision=FP16
2026.04
4,850
-
INT8-PPO
Precision=INT8
2026.04
4,720
-
INT4-PPO
Precision=INT4
2026.04
4,480
-
BitRL-1bit
Precision=1-bit
2026.04
4,210
86.8
MLP-PPO
Architecture=MLP
2026.04
3,980
-
Feedback
Search any
task
Search any
task