List your company

Gait Optimization on Towing Tank Single Limb (test)

48.58Episode RewardPPO (w/o Cost)
25.419231.432137.44543.4579Mar 4, 2026

Evaluation results

MethodLinks
PPO (w/o Cost)cost_signal=ignored2026.0348.580.391
ACPPO-PID2026.0345.190.235
PPO-Penaltyobjective=scalar penalty on reward2026.0343.460.314
ACPPO-PID (w/o Cycle Loss)cycle_loss=false2026.0343.350.271
CPPO-PID2026.0339.580.249
ACPPO-PID (w/o Asym Clip)asymmetric_clipping=false2026.0338.660.212
CPPO-PID-Hexploration=fixed clip [1−ϵ, 1+ϵhi]2026.0337.10.261
BFtype=sinusoidal paddling policy2026.0326.310.332