Papers with Code 아카이브
Humanoid Control
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills
SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending
Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners
FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control
One Policy but Many Worlds: A Scalable Unified Policy for Versatile Humanoid Locomotion
HuB: Learning Extreme Humanoid Balance
Visual Imitation Enables Contextual Humanoid Control
Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models
Reinforcement learning-based motion imitation for physiologically plausible musculoskeletal motor control
Humanoid-VLA: Towards Universal Humanoid Control with Visual Integration
Safe Bayesian Optimization for the Control of High-Dimensional Embodied Systems
Learning from Massive Human Videos for Universal Humanoid Pose Control
Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Robot Learning
The Role of Domain Randomization in Training Diffusion Policies for Whole-Body Humanoid Control
MuJoCo MPC for Humanoid Control: Evaluation on HumanoidBench
CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics
Hierarchical World Models as Visual Whole-Body Humanoid Controllers
Real-Time Simulated Avatar from Head-Mounted Sensors
Humanoid Locomotion as Next Token Prediction
H-GAP: Humanoid Control with a Generalist Planner
Universal Humanoid Motion Representations for Physics-Based Control
Perpetual Humanoid Control for Real-time Simulated Avatars
MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control
QuickPose: Real-time Multi-view Multi-person Pose Estimation in Crowded Scenes
From Universal Humanoid Control to Automatic Physically Valid Character Creation
Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress
Learning to Brachiate via Simplified Model Imitation
Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning
On the Emergence of Whole-body Strategies from Humanoid Robot Push-recovery Learning
Distributionally Robust Trajectory Optimization Under Uncertain Dynamics via Relative Entropy Trust-Regions
On the model-based stochastic value gradient for continuous reinforcement learning
ClipUp: A Simple and Powerful Optimizer for Distribution-based Policy Evolution
Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis
Optical Non-Line-of-Sight Physics-based 3D Human Pose Estimation
Rigorous Agent Evaluation: An Adversarial Approach to Uncover Catastrophic Failures
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.