List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on Hopper random

32.2Normalized ScoreAnti-exploration Method
-0.1448.25316.6525.047Dec 2, 2025Dec 13, 2025Dec 24, 2025Jan 5, 2026Jan 16, 2026Jan 27, 2026Feb 8, 2026
Updated 8mo ago

Evaluation results

MethodLinks
Anti-exploration Method2026.0232.2
GPC-SAC2026.0231.4
SAC-RND2026.0231.3
DMG2026.0220.4
CQL2026.0216.4
TD3-CVAE2026.0211.7
IQL2026.027.8
OTDF2025.124.4
IGDF2025.124.1
DVDF-OTDF2025.124
DVDF-IGDF2025.123.8
IQL2025.123.7
DARA2025.123.4
BOSA2025.121.1