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

Neural cellular automata (Neural CA) are a recent framework used to modelbiological phenomena emerging from multicellular organisms. In these systems,artificial neural networks are used as update rules for cellular automata.Neural CA are end-to-end differentiable systems where the parameters of theneural network can be learned to achieve a particular task. In this work, weused neural CA to control a cart-pole agent. The observations of theenvironment are transmitted in input cells, while the values of output cellsare used as a readout of the system. We trained the model using deep-Qlearning, where the states of the output cells were used as the Q-valueestimates to be optimized. We found that the computing abilities of thecellular automata were maintained over several hundreds of thousands ofiterations, producing an emergent stable behavior in the environment itcontrols for thousands of steps. Moreover, the system demonstrated life-likephenomena such as a developmental phase, regeneration after damage, stabilitydespite a noisy environment, and robustness to unseen disruption such as inputdeletion.

Towards self-organized control: Using neural cellular automata to robustly control a cart-pole agent