List your company

Offline Actor-Critic Optimization on Gymnasium LunarLander

-25.726Actor LossMA-SOBA
-26.523-21.14325-15.7635-10.38375Jun 21, 2026

Evaluation results

MethodLinks
MA-SOBASeeds=52026.06-25.7260.0040.4590.621
RQ-TTSASeeds=52026.06-25.7210.0030.4570.464
TTSASeeds=52026.06-25.6610.0060.430.383
ψ-VariantSeeds=52026.06-25.6190.0070.2470.649
AccBOSeeds=52026.06-12.8631.0890.0811.55
BiSLSSeeds=52026.06-5.8010.4340.0321.781