List your company

Locomotion on D4RL hopper v2 (medium)

103Normalized ReturnCPQL
22.19243.17164.1585.129Mar 10, 2026Mar 20, 2026Mar 31, 2026Apr 11, 2026Apr 22, 2026May 3, 2026May 14, 2026

Evaluation results

MethodLinks
CPQLGradient steps=1M2026.05103
QDQGradient steps=1M2026.05102.4
EDACGradient steps=3M2026.05101.6
EDACGradient steps=3M2026.05101
PBRLGradient steps=1M2026.05100.7
CPQLGradient steps=1M2026.0599.7
QDQGradient steps=1M2026.0599
SPAARSEnvironment steps=300k, Number of seeds=32026.0392.7
TTGradient steps=1M2026.0591.5
DTGradient steps=1M2026.0582.7
PBRLGradient steps=1M2026.0581.6
DTGradient steps=1M2026.0567.6
IQLEnvironment steps=300k, Number of seeds=32026.0366.3
TTGradient steps=1M2026.0561.1
UWACGradient steps=1M2026.0550.9
UWACGradient steps=1M2026.0525.3