Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Language-Conditioned Tasks on BabyAIGoToRedBall
Loading...
0.92
Mean Episodic Return
FP16-PPO
0.6392
0.7121
0.785
0.8579
Apr 27, 2026
Mean Episodic Return
FP16 Percentage
Updated 1mo ago
Evaluation Results
Method
Method
Links
Mean Episodic Return
FP16 Percentage
FP16-PPO
Precision=FP16
2026.04
0.92
-
INT8-PPO
Precision=INT8
2026.04
0.9
-
BitRL-1bit
Precision=1-bit
2026.04
0.88
95.7
INT4-PPO
Precision=INT4
2026.04
0.87
-
MLP-PPO
Architecture=MLP
2026.04
0.65
-
Feedback
Search any
task
Search any
task