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

Home/Benchmarks

Motion Imitation on Humanoid Spinkick

77Normalized Return

AWR

Updated 1mo ago

Evaluation Results

Method	Links
AWR 2019.10		77
PPO 2019.10		70
RWR 2019.10		5

SOTA Paper

AWR

Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning

Dataset

Humanoid

Follow for update

@wizwand_team Discord

Related Benchmarks

Reinforcement Learning on LunarLander v2 Reinforcement Learning on Ant v2 Reinforcement Learning on HalfCheetah v2 Reinforcement Learning on Hopper v2 Reinforcement Learning on Humanoid v2

© 2026 wizwand

Blog Contact Changelog Swarm

Privacy Policy Terms of Service FAQs Swarm Docs