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

We study the problem of experiment design to learn causal structures frominterventional data. We consider an active learning setting in which theexperimenter decides to intervene on one of the variables in the system in eachstep and uses the results of the intervention to recover further causalrelationships among the variables. The goal is to fully identify the causalstructures with minimum number of interventions. We present the first deepreinforcement learning based solution for the problem of experiment design. Inthe proposed method, we embed input graphs to vectors using a graph neuralnetwork and feed them to another neural network which outputs a variable forperforming intervention in each step. Both networks are trained jointly via aQ-iteration algorithm. Experimental results show that the proposed methodachieves competitive performance in recovering causal structures with respectto previous works, while significantly reducing execution time in dense graphs.

Active Learning of Causal Structures with Deep Reinforcement Learning