English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Compositional generalization is a critical ability in learning anddecision-making. We focus on the setting of reinforcement learning inobject-oriented environments to study compositional generalization in worldmodeling. We (1) formalize the compositional generalization problem with analgebraic approach and (2) study how a world model can achieve that. Weintroduce a conceptual environment, Object Library, and two instances, anddeploy a principled pipeline to measure the generalization ability. Motivatedby the formulation, we analyze several methods with exact or no compositionalgeneralization ability using our framework, and design a differentiableapproach, Homomorphic Object-oriented World Model (HOWM), that achieves softbut more efficient compositional generalization.

Toward Compositional Generalization in Object-Oriented World Modeling