Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Classic Discrete Control on Acrobot v1
Loading...
94
Mean Episodic Return
BitRL-1bit
81.52
84.76
88
91.24
Apr 27, 2026
Mean Episodic Return
FP16 Usage (%)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Mean Episodic Return
FP16 Usage (%)
BitRL-1bit
Precision=1-bit
2026.04
94
87.1
INT4-PPO
Precision=INT4
2026.04
89
-
MLP-PPO
Architecture=MLP
2026.04
88
-
INT8-PPO
Precision=INT8
2026.04
85
-
FP16-PPO
Precision=FP16
2026.04
82
-
Feedback
Search any
task
Search any
task