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

Home/Benchmarks

Run on Quadruped

425.9Average Return

Online FB-PbRL

Updated 1d ago

Evaluation Results

Method	Links
Online FB-PbRL 2026.05		425.9
PrefPPO 2026.05		198.6

SOTA Paper

Online FB-PbRL

From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning

Dataset

Quadruped

Follow for update

@wizwand_team Discord

Related Benchmarks

Reinforcement Learning on DMC Cheetah Reinforcement Learning on DMC Walker Reinforcement Learning on DMC Quadruped Reinforcement Learning on DMC PointMass Manipulation on Adroit Pen-cloned (human-labeled)

© 2026 wizwand

Blog Contact Changelog Swarm

Privacy Policy Terms of Service FAQs Swarm Docs