ModSkill: Physical Character Skill Modularization
Human motion is highly diverse and dynamic, posing challenges for imitation learning algorithms that aim to generalize motor skills for controlling simulated characters. Previous methods typically rely on a universal full-body controller for tracking reference motion (tracking-based model) or a unified full-body skill embedding space (skill embedding). However, these approaches often struggle to generalize and scale to larger motion datasets. In this work, we introduce a novel skill learning framework, ModSkill, that decouples complex full-body skills into compositional, modular skills for independent body parts. Our framework features a skill modularization attention layer that processes policy observations into modular skill embeddings that guide low-level controllers for each body part. We also propose an Active Skill Learning approach with Generative Adaptive Sampling, using large motion generation models to adaptively enhance policy learning in challenging tracking scenarios. Our results show that this modularized skill learning framework, enhanced by generative sampling, outperforms existing methods in precise full-body motion tracking and enables reusable skill embeddings for diverse goal-driven tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
Imitation LearningMotion GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Unsupervised Skill Discovery through Skill Regions Differentiation
Unsupervised Reinforcement Learning (RL) aims to discover diverse behaviors that can accelerate the learning of downstream tasks. Previous methods typically focus on entropy-based exploration or empowerment-driven skill …
Density EstimationReinforcement Learning (RL)Unsupervised Reinforcement LearningChain-of-Skills: A Configurable Model for Open-domain Question Answering
The retrieval model is an indispensable component for real-world knowledge-intensive tasks, e.g., open-domain question answering (ODQA). As separate retrieval skills are annotated for different datasets, recent work focu…
Open-Domain Question AnsweringQuestion AnsweringRetrievalWorld KnowledgeHierarchical Primitive Composition: Simultaneous Activation of Skills with Inconsistent Action Dimensions in Multiple Hierarchies
Deep reinforcement learning has shown its effectiveness in various applications, providing a promising direction for solving tasks with high complexity. However, naively applying classical RL for learning a complex long-…
Deep Reinforcement LearningHierarchical Reinforcement LearningC$\cdot$ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characters
We present C$\cdot$ASE, an efficient and effective framework that learns conditional Adversarial Skill Embeddings for physics-based characters. Our physically simulated character can learn a diverse repertoire of skills …
Imitation LearningASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters
The incredible feats of athleticism demonstrated by humans are made possible in part by a vast repertoire of general-purpose motor skills, acquired through years of practice and experience. These skills not only enable h…
GPUImitation LearningUnsupervised Reinforcement Learning