List your company

Reinforcement Learning on Halfcheetah v5

13,996.2Average ReturnSAC+TQC
-171.9283,506.3367,184.610,862.864Feb 5, 2026Feb 19, 2026Mar 5, 2026Mar 19, 2026Apr 2, 2026Apr 16, 2026Apr 30, 2026

Evaluation results

MethodLinks
SAC+TQCAlgorithm=SAC, Critic=TQC2026.0213,996.2——
TD3+DBC(*)Algorithm=TD3, Critic=DBC2026.0213,787.8——
QVPO+DBC(*)Algorithm=QVPO, Critic=DBC2026.0213,182.1——
SAC+DBC(*)Algorithm=SAC, Critic=DBC2026.0213,120.2——
SAC+DSACAlgorithm=SAC, Critic=DSAC2026.0212,974——
SAC+CDQAlgorithm=SAC, Critic=CDQ2026.0212,776.4——
Full State SACState Dim Removed=None2026.0212,400——
Full State SACState Dim Removed=None2026.0212,400——
QVPO+CDQAlgorithm=QVPO, Critic=CDQ2026.0212,103.9——
TD3+CDQAlgorithm=TD3, Critic=CDQ2026.0211,679——
SAC+IQNAlgorithm=SAC, Critic=IQN2026.0210,930.2——
Recurrent SACState Dim Removed=32026.0210,057——
Recurrent SACState Dim Removed=32026.029,875——
TFM-S3-TD3Algorithm=TFM-S3-TD3, Variant=proposed2026.049,863.440.562.7
CQLState Dim Removed=32026.029,748——
CQLState Dim Removed=32026.029,748——
Random Search TD3Algorithm=Random Search, Candidates=322026.049,686.338.466
TD3Algorithm=TD3, Variant=vanilla2026.049,624.139.671.3
TFM-S3-TD3Algorithm=TFM-S3-TD3, Variant=One shot2026.049,576.937.768
T-REXState Dim Removed=32026.029,120——
TrexState Dim Removed=32026.029,106——
Causal PBRSState Dim Removed=32026.028,954——
Causal PBRSState Dim Removed=32026.028,949——
BaselineState Dim Removed=32026.028,931——
SAC BaselineState Dim Removed=32026.028,931——
SAC+VFAlgorithm=SAC, Critic=VF2026.028,199.5——
Recurrent SACState Dim Removed=12026.027,957——
Recurrent SACState Dim Removed=82026.027,939——
Recurrent SACState Dim Removed=82026.027,939——
Recurrent SACState Dim Removed=12026.027,378——
SAC+VDAlgorithm=SAC, Critic=VD2026.024,284.8——
T-REXState Dim Removed=12026.022,059——
TrexState Dim Removed=12026.022,057——
Causal PBRSState Dim Removed=12026.022,055——
Causal PBRSState Dim Removed=12026.022,051——
CQLState Dim Removed=12026.022,039——
CQLState Dim Removed=12026.022,039——
BaselineState Dim Removed=12026.022,013——
SAC BaselineState Dim Removed=12026.022,013——
Causal PBRSState Dim Removed=82026.021,103——
Causal PBRSState Dim Removed=82026.021,103——
SAC BaselineState Dim Removed=82026.02896——
BaselineState Dim Removed=82026.02895——
T-REXState Dim Removed=82026.02615——
TrexState Dim Removed=82026.02612——
CQLState Dim Removed=82026.02373——
CQLState Dim Removed=82026.02373——