paper-with-me

Papers

Controllability-Aware Unsupervised Skill Discovery

2023-02-10 · Seohong Park, Kimin Lee, Youngwoon Lee, Pieter Abbeel

One of the key capabilities of intelligent agents is the ability to discover useful skills without external supervision. However, the current unsupervised skill discovery methods are often limited to acquiring simple, easy-to-learn skills due to the lack of incentives to discover more complex, challenging behaviors. We introduce a novel unsupervised skill discovery method, Controllability-aware Skill Discovery (CSD), which actively seeks complex, hard-to-control skills without supervision. The key component of CSD is a controllability-aware distance function, which assigns larger values to state transitions that are harder to achieve with the current skills. Combined with distance-maximizing skill discovery, CSD progressively learns more challenging skills over the course of training as our jointly trained distance function reduces rewards for easy-to-achieve skills. Our experimental results in six robotic manipulation and locomotion environments demonstrate that CSD can discover diverse complex skills including object manipulation and locomotion skills with no supervision, significantly outperforming prior unsupervised skill discovery methods. Videos and code are available at https://seohong.me/projects/csd/

📄 PDF Abstract BibTeX arXiv:2302.05103

Code (3)

artberryx/csd-public 공식 구현
seohongpark/CSD-manipulation 공식 구현
seohongpark/csd-locomotion 공식 구현 tf

Similar Papers 제목 키워드 기반

Dynamics-Aware Unsupervised Skill Discovery

2020-05-01 · ICLR 2020 1 · Archit Sharma, Shixiang Gu, Sergey Levine, Vikash Kumar 외

Conventionally, model-based reinforcement learning (MBRL) aims to learn a global model for the dynamics of the environment. A good model can potentially enable planning algorithms to generate a large variety of behaviors…

Model-based Reinforcement Learning

Dynamics-Aware Unsupervised Discovery of Skills

2019-07-02 · Archit Sharma, Shixiang Gu, Sergey Levine, Vikash Kumar 외

Conventionally, model-based reinforcement learning (MBRL) aims to learn a global model for the dynamics of the environment. A good model can potentially enable planning algorithms to generate a large variety of behaviors…

Model-based Reinforcement LearningReinforcement Learning

Group-Invariant Unsupervised Skill Discovery: Symmetry-aware Skill Representations for Generalizable Behavior

2026-01-20 · Junwoo Chang, Joseph Park, Roberto Horowitz, Jongmin Lee 외 arxiv

Unsupervised skill discovery aims to acquire behavior primitives that improve exploration and accelerate downstream task learning. However, existing approaches often ignore the geometric symmetries of physical environmen…

Efficient Skill Discovery via Regret-Aware Optimization

2025-06-26 · He Zhang, Ming Zhou, Shaopeng Zhai, Ying Sun 외

Unsupervised skill discovery aims to learn diverse and distinguishable behaviors in open-ended reinforcement learning. For existing methods, they focus on improving diversity through pure exploration, mutual information …

DiversityRepresentation Learning

Unsupervised Skill Discovery with Bottleneck Option Learning

2021-06-27 · Jaekyeom Kim, Seohong Park, Gunhee Kim

Having the ability to acquire inherent skills from environments without any external rewards or supervision like humans is an important problem. We propose a novel unsupervised skill discovery method named Information Bo…

DisentanglementMuJoCo