SOTAVerified

Humanoid Control

Control of a high-dimensional humanoid. This can include skill learning by tracking motion capture clips, learning goal-directed tasks like going towards a moving target, and generating motion within a physics simulator.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 37 papers

TitleStatusHype
KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills—0
RL from Physical Feedback: Aligning Large Motion Models with Humanoid Control—0
SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill BlendingCode2
Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners—0
FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control—0
One Policy but Many Worlds: A Scalable Unified Policy for Versatile Humanoid Locomotion—0
HuB: Learning Extreme Humanoid Balance—0
Visual Imitation Enables Contextual Humanoid Control—0
Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation ModelsCode4
Reinforcement learning-based motion imitation for physiologically plausible musculoskeletal motor controlCode2
Show:102550
← PrevPage 1 of 4Next →

No leaderboard results yet.