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

Current domain-independent, classical planners require symbolic models of theproblem domain and instance as input, resulting in a knowledge acquisitionbottleneck. Meanwhile, although deep learning has achieved significant successin many fields, the knowledge is encoded in a subsymbolic representation whichis incompatible with symbolic systems such as planners. We propose LatPlan, anunsupervised architecture combining deep learning and classical planning. Givenonly an unlabeled set of image pairs showing a subset of transitions allowed inthe environment (training inputs), and a pair of images representing theinitial and the goal states (planning inputs), LatPlan finds a plan to the goalstate in a symbolic latent space and returns a visualized plan execution. Thecontribution of this paper is twofold: (1) State Autoencoder, which finds apropositional state representation of the environment using a VariationalAutoencoder. It generates a discrete latent vector from the images, based onwhich a PDDL model can be constructed and then solved by an off-the-shelfplanner. (2) Action Autoencoder / Discriminator, a neural architecture whichjointly finds the action symbols and the implicit action models(preconditions/effects), and provides a successor function for the implicitgraph search. We evaluate LatPlan using image-based versions of 3 planningdomains: 8-puzzle, Towers of Hanoi and LightsOut.

Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary