List your company

Reinforcement Learning on Walker2D v5

6,335.5Average ReturnTD3+DBC(*)
-45.1081,611.3963,267.94,924.404Jun 8, 2025Jul 19, 2025Aug 29, 2025Oct 9, 2025Nov 19, 2025Dec 30, 2025Feb 10, 2026

Evaluation results

MethodLinks
TD3+DBC(*)Algorithm=TD3, Critic=DBC2026.026,335.5—
SAC+DBC(*)Algorithm=SAC, Critic=DBC2026.026,138.2—
SAC+TQCAlgorithm=SAC, Critic=TQC2026.025,802.6—
QVPO+DBC(*)Algorithm=QVPO, Critic=DBC2026.025,448.1—
TD3+CDQAlgorithm=TD3, Critic=CDQ2026.025,093.7—
QVPO+CDQAlgorithm=QVPO, Critic=CDQ2026.024,986.3—
SAC+CDQAlgorithm=SAC, Critic=CDQ2026.024,854.4—
SAC+IQNAlgorithm=SAC, Critic=IQN2026.024,766.5—
T-REXState Dim Removed=102026.024,417—
TrexState Dim Removed=102026.024,385—
Causal PBRSState Dim Removed=82026.024,295—
Full State SACState Dim Removed=None2026.024,050—
Full State SACState Dim Removed=None2026.024,050—
T-REXState Dim Removed=62026.024,045—
SAC BaselineState Dim Removed=62026.023,981—
Causal PBRSState Dim Removed=102026.023,950—
BaselineState Dim Removed=102026.023,925—
SAC BaselineState Dim Removed=102026.023,925—
Causal PBRSState Dim Removed=62026.023,899—
BaselineState Dim Removed=62026.023,893—
Causal PBRSState Dim Removed=62026.023,884—
Causal PBRSState Dim Removed=102026.023,814—
CQLState Dim Removed=82026.023,766—
CQLState Dim Removed=82026.023,708—
SAC BaselineState Dim Removed=82026.023,640—
Causal PBRSState Dim Removed=82026.023,632—
TrexState Dim Removed=62026.023,603—
CQLState Dim Removed=102026.023,600—
BaselineState Dim Removed=82026.023,580—
CQLState Dim Removed=102026.023,424—
SAC+DSACAlgorithm=SAC, Critic=DSAC2026.023,297.4—
CQLState Dim Removed=62026.023,243—
CQLState Dim Removed=62026.023,132—
T-REXState Dim Removed=82026.022,830—
TrexState Dim Removed=82026.022,663—
SAC+VFAlgorithm=SAC, Critic=VF2026.022,626.4—
SAC+VDAlgorithm=SAC, Critic=VD2026.022,533.9—
Recurrent SACState Dim Removed=62026.022,210—
Recurrent SACState Dim Removed=62026.022,181—
Recurrent SACState Dim Removed=102026.021,351—
Recurrent SACState Dim Removed=102026.021,124—
Recurrent SACState Dim Removed=82026.021,105—
Recurrent SACState Dim Removed=82026.02942—
RPIDDPG2025.06319.9245
DDPG2025.06200.3165.7