List your company
ResearchFormerly WizWand

Offline-to-Online Reinforcement Learning on hammer-cloned v1

46.74Average Online Expected ReturnDUAL
-1.599210.950423.536.0496May 29, 2026
Updated 5mo ago

Evaluation results

MethodLinks
DUALCritic framework=IQL, Online training time steps=1M, Random seeds=52026.0546.74
Diff-QLCritic framework=IQL, Online training time steps=1M, Random seeds=52026.0533.82
EDISCritic framework=IQL, Online training time steps=1M, Random seeds=52026.0528
BaseCritic framework=IQL, Online training time steps=1M, Random seeds=52026.0527.41
DUALCritic framework=Cal-QL, Online training time steps=1M, Random seeds=52026.050.68
EDISCritic framework=Cal-QL, Online training time steps=1M, Random seeds=52026.050.35
Diff-QLCritic framework=Cal-QL, Online training time steps=1M, Random seeds=52026.050.32
BaseCritic framework=Cal-QL, Online training time steps=1M, Random seeds=52026.050.26