Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safe Reinforcement Learning on Hopper-Velocity
Loading...
1,554.56
Reward
RCPO
1,162.0952
1,263.9851
1,365.875
1,467.7649
Jan 26, 2026
Reward
Cost
Episode Length
Updated 1mo ago
Evaluation Results
Method
Method
Links
Reward
Cost
Episode Length
RCPO
2026.01
1,554.56
37.53
979.3
TRPO-ADRC
2026.01
1,470.61
10.67
1,000
CUP
2026.01
1,326.84
26.9
854.4
CPPO-ADRC
2026.01
1,322.83
10.43
910.2
RCPO-ADRC
2026.01
1,248.94
9.27
818.1
IPO
2026.01
1,216.01
27.57
797.33
PDO
2026.01
1,177.19
18.03
797.57
Feedback
Search any
task
Search any
task