DeepAI AI Chat
Log In Sign Up

Lipschitz-constrained Unsupervised Skill Discovery

by   Seohong Park, et al.

We study the problem of unsupervised skill discovery, whose goal is to learn a set of diverse and useful skills with no external reward. There have been a number of skill discovery methods based on maximizing the mutual information (MI) between skills and states. However, we point out that their MI objectives usually prefer static skills to dynamic ones, which may hinder the application for downstream tasks. To address this issue, we propose Lipschitz-constrained Skill Discovery (LSD), which encourages the agent to discover more diverse, dynamic, and far-reaching skills. Another benefit of LSD is that its learned representation function can be utilized for solving goal-following downstream tasks even in a zero-shot manner - i.e., without further training or complex planning. Through experiments on various MuJoCo robotic locomotion and manipulation environments, we demonstrate that LSD outperforms previous approaches in terms of skill diversity, state space coverage, and performance on seven downstream tasks including the challenging task of following multiple goals on Humanoid. Our code and videos are available at


page 22

page 23

page 24


Controllability-Aware Unsupervised Skill Discovery

One of the key capabilities of intelligent agents is the ability to disc...

Unsupervised Reinforcement Learning for Transferable Manipulation Skill Discovery

Current reinforcement learning (RL) in robotics often experiences diffic...

Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching

Learning meaningful behaviors in the absence of reward is a difficult pr...

Discovering and Achieving Goals via World Models

How can artificial agents learn to solve many diverse tasks in complex v...

Dynamics-Aware Quality-Diversity for Efficient Learning of Skill Repertoires

Quality-Diversity (QD) algorithms are powerful exploration algorithms th...

Choreographer: Learning and Adapting Skills in Imagination

Unsupervised skill learning aims to learn a rich repertoire of behaviors...

Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviors

We investigate the use of prior knowledge of human and animal movement t...

Code Repositories


Lipschitz-constrained Unsupervised Skill Discovery

view repo