Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Continuous Control on DM Control pendulum-swingup
Loading...
0.56
Average Reward
RC-SAC
0.4872
0.5061
0.525
0.5439
Mar 5, 2026
Average Reward
Updated 2mo ago
Evaluation Results
Method
Method
Links
Average Reward
RC-SAC
training steps=50 [k],...
2026.03
0.56
RC-TD3
training steps=50 [k],...
2026.03
0.53
TD3
training steps=50 [k],...
2026.03
0.49
SAC
training steps=50 [k],...
2026.03
0.49
Feedback
Search any
task
Search any
task