Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Continuous Control on Hopper v5
Loading...
3,732.5
Average Return
DBC
945.508
1,669.054
2,392.6
3,116.146
Feb 5, 2026
Feb 15, 2026
Feb 26, 2026
Mar 9, 2026
Mar 19, 2026
Mar 30, 2026
Apr 10, 2026
Average Return
Updated 6d ago
Evaluation Results
Method
Method
Links
Average Return
DBC
Actor Backbone=SAC
2026.02
3,732.5
TQC
Actor Backbone=SAC
2026.02
3,704.6
SAC
Actor Backbone=SAC
2026.02
3,630.5
DSAC
Actor Backbone=SAC
2026.02
3,522.9
TRFP(ours)
NFE=4 × 4
2026.04
3,507.5
TRFP(one-step)
NFE=1 × 4
2026.04
3,440.6
VF
Actor Backbone=SAC
2026.02
3,310.4
IQN
Actor Backbone=SAC
2026.02
3,301.8
TD3
NFE=1
2026.04
3,015.6
MaxEntDP
NFE=20 × 10
2026.04
3,000.6
PDA
Environment steps=1M,...
2026.03
2,693.9
SDAC
NFE=20 × 32
2026.04
2,591.3
PPO
Environment steps=1M,...
2026.03
2,397.8
SAC
NFE=1
2026.04
2,220.6
VD
Actor Backbone=SAC
2026.02
1,052.7
Feedback
Search any
task
Search any
task