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 present an approach for designing swarm-based optimizers for the globaloptimization of expensive black-box functions. In the proposed approach, theproblem of finding efficient optimizers is framed as a reinforcement learningproblem, where the goal is to find optimization policies that require a fewfunction evaluations to converge to the global optimum. The state of each agentwithin the swarm is defined as its current position and function value within adesign space and the agents learn to take favorable actions that maximizereward, which is based on the final value of the objective function. Theproposed approach is tested on various benchmark optimization functions andcompared to the performance of other global optimization strategies.Furthermore, the effect of changing the number of agents, as well as thegeneralization capabilities of the trained agents are investigated. The resultsshow superior performance compared to the other optimizers, desired scalingwhen the number of agents is varied, and acceptable performance even whenapplied to unseen functions. On a broader scale, the results show promise forthe rapid development of domain-specific optimizers.

DeepHive: A multi-agent reinforcement learning approach for automated discovery of swarm-based optimization policies