List your company
ResearchFormerly WizWand

Reinforcement Learning on PointMaze Large v3

1.02Avg AUC (z-scored)TD3
0.02160.28080.540.7992Jun 15, 2026
Updated 4mo ago

Evaluation results

MethodLinks
TD3Noise Type=OU2026.061.02
TD3Noise Type=Red2026.060.76
SACNoise Type=White2026.060.6
TD3Noise Type=White2026.060.51
TD3Noise Type=Rose2026.060.46
TD3Noise Type=Pink2026.060.43
SACNoise Type=Blush2026.060.32
SACNoise Type=Rose2026.060.28
SACNoise Type=Red2026.060.23
TD3Noise Type=Baby2026.060.18
SACNoise Type=Pink2026.060.16
SACNoise Type=Baby2026.060.07
TD3Noise Type=Blush2026.060.06