Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Continuous Control on DM Control fish-swim
Loading...
0.51
Average Reward
TD3
0.3748
0.4099
0.445
0.4801
Mar 5, 2026
Average Reward
Updated 2mo ago
Evaluation Results
Method
Method
Links
Average Reward
TD3
training steps=50 [k],...
2026.03
0.51
RC-SAC
training steps=50 [k],...
2026.03
0.48
SAC
training steps=50 [k],...
2026.03
0.47
RC-TD3
training steps=50 [k],...
2026.03
0.38
Feedback
Search any
task
Search any
task
