List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on HalfCheetah random

33.8Normalized ScoreAnti-exploration Method
-1.3527.77416.926.026Dec 2, 2025Dec 13, 2025Dec 24, 2025Jan 5, 2026Jan 16, 2026Jan 27, 2026Feb 8, 2026
Updated 8mo ago

Evaluation results

MethodLinks
Anti-exploration Method2026.0233.8
GPC-SAC2026.0231
SAC-RND2026.0229
DMG2026.0228.8
TD3-CVAE2026.0228.6
CQL2026.0228.3
IQL2026.0211
BOSA2025.122.2
DVDF-OTDF2025.122.2
DARA2025.122
OTDF2025.122
IQL2025.120
IGDF2025.120
DVDF-IGDF2025.120