Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reinforcement Learning on Acrobot (AB) (test)
Loading...
80
Avg Undiscounted Reward
SYMPOL
-216.4
-139.45
-62.5
14.45
Mar 11, 2026
Avg Undiscounted Reward
Updated 1mo ago
Evaluation Results
Method
Method
Links
Avg Undiscounted Reward
SYMPOL
Number of random trial...
2026.03
80
SDT
Number of random trial...
2026.03
77
SA-DT
Depth (d)=8, Number of...
2026.03
75
MLP
Number of random trial...
2026.03
72
SA-DT
Depth (d)=5, Number of...
2026.03
-97
D-SDT
Number of random trial...
2026.03
-205
Feedback
Search any
task
Search any
task
