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

Home/Benchmarks

Off-Policy Evaluation on General Function Approximation completeness

2Coverage

Q-MMR

Updated 26d ago

Evaluation Results

Method	Links
Q-MMR 2026.05		2	-

SOTA Paper

Q-MMR

Q-MMR: Off-Policy Evaluation via Recursive Reweighting and Moment Matching

Dataset

General Function Approximation

Follow for update

@wizwand_team Discord

Related Benchmarks

Off-Policy Evaluation on General Function Approximation realizability Off-Policy Evaluation on Linear Function Approximation completeness Off-Policy Evaluation on Linear Function Approximation + realizability

© 2026 wizwand

Blog Contact Changelog Swarm

Privacy Policy Terms of Service FAQs Swarm Docs