List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on Walker2d random

21.5Normalized ScoreSAC-RND
-0.864.94510.7516.555Dec 2, 2025Dec 13, 2025Dec 24, 2025Jan 5, 2026Jan 16, 2026Jan 27, 2026Feb 8, 2026
Updated 8mo ago

Evaluation results

MethodLinks
SAC-RND2026.0221.5
GPC-SAC2026.029.6
Anti-exploration Method2026.028.4
IQL2026.026.4
TD3-CVAE2026.025.5
DMG2026.024.8
CQL2026.024.2
IQL2025.120
BOSA2025.120
DARA2025.120
IGDF2025.120
DVDF-IGDF2025.120
OTDF2025.120
DVDF-OTDF2025.120