Timezone: »

 
Spotlight
Unsupervised Skill Discovery with Bottleneck Option Learning
Jaekyeom Kim · Seohong Park · Gunhee Kim

Wed Jul 21 05:30 AM -- 05:35 AM (PDT) @
in Reinforcement Learning 11 »

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. Our code is available at https://vision.snu.ac.kr/projects/ibol.

Keywords: Reinforcement Learning and Planning · Deep RL

Author Information

Jaekyeom Kim (Seoul National University)
Seohong Park (Seoul National University)
Gunhee Kim (Seoul National University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors