Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Reinforcement Learning on Hopper delta=[0.2, 0.5, 0.5], kappa=2.5 v5 (test)

3,312Return

DD-SRad

750.481,415.492,080.52,745.51May 5, 2026
Updated 27d ago

Evaluation Results

MethodLinks
2026.05
3,31211.646.2
2026.05
3,256630.3
2026.05
2,7128.449.6
2026.05
2,610746.1
2026.05
2,39413.416.6
2026.05
2,33411.848
2026.05
2,319926.7
2026.05
2,19533.515.5
2026.05
1,62420.437
2026.05
1,27812.935.3
2026.05
1,02013.633.3
2026.05
84929.648.7