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

Home/Benchmarks

Off-policy Evaluation on D4RL Walker2D-random

0.879RMAE

ROPE

Updated 1mo ago

Evaluation Results

Method	Links
ROPE 2023.10		0.879
BCRL 2023.10		1.022

SOTA Paper

ROPE

State-Action Similarity-Based Representations for Off-Policy Evaluation

Dataset

D4RL

Follow for update

@wizwand_team Discord

Related Benchmarks

Off-policy Evaluation on D4RL HalfCheetah-random Off-policy Evaluation on D4RL HalfCheetah medium Off-policy Evaluation on D4RL HalfCheetah medium-expert Off-policy Evaluation on D4RL Walker2D-medium Off-policy Evaluation on D4RL Walker2D-medium-expert

© 2026 wizwand

Blog Contact Changelog Swarm

Privacy Policy Terms of Service FAQs Swarm Docs