List your company
ResearchFormerly WizWand

Reinforcement Learning on AdroitHandDoor v1

1,725Average ReturnCausal PBRS
-109.872366.489842.851,319.211Sep 24, 2025Oct 17, 2025Nov 9, 2025Dec 2, 2025Dec 25, 2025Jan 17, 2026Feb 10, 2026
Updated 8mo ago

Evaluation results

MethodLinks
Causal PBRSState Dim Removed=12026.021,725
T-REXState Dim Removed=12026.021,659
SAC BaselineState Dim Removed=12026.021,472
Causal PBRSState Dim Removed=12026.021,289
CQLState Dim Removed=12026.02415
CQLState Dim Removed=12026.02308
TrexState Dim Removed=12026.02105
BaselineState Dim Removed=12026.0271
Recurrent SACState Dim Removed=12026.02-27
Recurrent SACState Dim Removed=12026.02-27
Log-barrier DDPG2025.09-36
DDPG2025.09-39.3