Offline Reinforcement Learning on Walker2d random benchmark leaderboard · SOTA2 Research

Offline Reinforcement Learning on Walker2d random

21.5Normalized ScoreSAC-RND

Evaluation Results

Method	Links
SAC-RND2026.02		21.5
GPC-SAC2026.02		9.6
Anti-exploration Method2026.02		8.4
IQL2026.02		6.4
TD3-CVAE2026.02		5.5
DMG2026.02		4.8
CQL2026.02		4.2
IQL2025.12		0
BOSA2025.12		0
DARA2025.12		0
IGDF2025.12		0
DVDF-IGDF2025.12		0
OTDF2025.12		0
DVDF-OTDF2025.12		0