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

Modeling a structured, dynamic environment like a video game requires keepingtrack of the objects and their states declarative knowledge) as well aspredicting how objects behave (procedural knowledge). Black-box models with amonolithic hidden state often fail to apply procedural knowledge consistentlyand uniformly, i.e., they lack systematicity. For example, in a video game,correct prediction of one enemy's trajectory does not ensure correct predictionof another's. We address this issue via an architecture that factorizesdeclarative and procedural knowledge and that imposes modularity within eachform of knowledge. The architecture consists of active modules called objectfiles that maintain the state of a single object and invoke passive externalknowledge sources called schemata that prescribe state updates. To use a videogame as an illustration, two enemies of the same type will share schemata butwill have separate object files to encode their distinct state (e.g., health,position). We propose to use attention to determine which object files toupdate, the selection of schemata, and the propagation of information betweenobject files. The resulting architecture is a drop-in replacement conforming tothe same input-output interface as normal recurrent networks (e.g., LSTM, GRU)yet achieves substantially better generalization on environments that havemultiple object tokens of the same type, including a challenging intuitivephysics benchmark.

Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems