Log In Sign Up

Unsupervised Skill Discovery with Bottleneck Option Learning

by   Jaekyeom Kim, et al.

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 Bottleneck Option Learning (IBOL). On top of the linearization of environments that promotes more various and distant state transitions, IBOL enables the discovery of diverse skills. It provides the abstraction of the skills learned with the information bottleneck framework for the options with improved stability and encouraged disentanglement. We empirically demonstrate that IBOL outperforms multiple state-of-the-art unsupervised skill discovery methods on the information-theoretic evaluations and downstream tasks in MuJoCo environments, including Ant, HalfCheetah, Hopper and D'Kitty.


One After Another: Learning Incremental Skills for a Changing World

Reward-free, unsupervised discovery of skills is an attractive alternati...

Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills

Acquiring abilities in the absence of a task-oriented reward function is...

Lipschitz-constrained Unsupervised Skill Discovery

We study the problem of unsupervised skill discovery, whose goal is to l...

Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learning

Option discovery and skill acquisition frameworks are integral to the fu...

MO2: Model-Based Offline Options

The ability to discover useful behaviours from past experience and trans...

ODPP: A Unified Algorithm Framework for Unsupervised Option Discovery based on Determinantal Point Process

Learning rich skills through temporal abstractions without supervision o...

Sociality and Skill Sharing in the Garden

Gardening is an activity that involves a number of dimensions of increas...