Offline Reinforcement Learning on Hopper random benchmark leaderboard · SOTA2 Research

Offline Reinforcement Learning on Hopper random

32.2Normalized ScoreAnti-exploration Method

Evaluation Results

Method	Links
Anti-exploration Method2026.02		32.2
GPC-SAC2026.02		31.4
SAC-RND2026.02		31.3
DMG2026.02		20.4
CQL2026.02		16.4
TD3-CVAE2026.02		11.7
IQL2026.02		7.8
OTDF2025.12		4.4
IGDF2025.12		4.1
DVDF-OTDF2025.12		4
DVDF-IGDF2025.12		3.8
IQL2025.12		3.7
DARA2025.12		3.4
BOSA2025.12		1.1