Share your thoughts, 1 month free Claude Pro on usSee more

Offline Reinforcement Learning on D4RL Maze maze2d-large v2 (test)

156.4Normalized Score

A2PO

Updated 1mo ago

Evaluation Results

Method	Links
A2PO 2024.03		156.4
TD3+BC 2024.03		128.5
Diffusion-QL 2024.03		116.3
LAPO 2024.03		69.7
EQL 2024.03		57
IQL 2024.03		45.7
AWAC 2024.03		43.9
BCQ 2024.03		43
CQL 2024.03		12.5
CQL+AW 2024.03		10.3
BC 2024.03		1.1
MOPO 2024.03		-0.5