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

In this paper, we leverage the efficiency of Binarized Neural Networks (BNNs)to learn complex state transition models of planning domains with discretizedfactored state and action spaces. In order to directly exploit this transitionstructure for planning, we present two novel compilations of the learnedfactored planning problem with BNNs based on reductions to Weighted PartialMaximum Boolean Satisfiability (FD-SAT-Plan+) as well as Binary LinearProgramming (FD-BLP-Plan+). Theoretically, we show that our SAT-basedBi-Directional Neuron Activation Encoding is asymptotically the most compactencoding relative to the current literature and supports Unit Propagation (UP)-- an important property that facilitates efficiency in SAT solvers.Experimentally, we validate the computational efficiency of our Bi-DirectionalNeuron Activation Encoding in comparison to an existing neuron activationencoding and demonstrate the ability to learn complex transition models withBNNs. We test the runtime efficiency of both FD-SAT-Plan+ and FD-BLP-Plan+ onthe learned factored planning problem showing that FD-SAT-Plan+ scales betterwith increasing BNN size and complexity. Finally, we present a finite-timeincremental constraint generation algorithm based on generalized landmarkconstraints to improve the planning accuracy of our encodings through simulatedor real-world interaction.

Compact and Efficient Encodings for Planning in Factored State and Action Spaces with Learned Binarized Neural Network Transition Models