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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Existing methods for optimal control struggle to deal with the complexitycommonly encountered in real-world systems, including dimensionality, processerror, model bias and data heterogeneity. Instead of tackling these systemcomplexities directly, researchers have typically sought to simplify models tofit optimal control methods. But when is the optimal solution to anapproximate, stylized model better than an approximate solution to a moreaccurate model? While this question has largely gone unanswered owing to thedifficulty of finding even approximate solutions for complex models, recentalgorithmic and computational advances in deep reinforcement learning (DRL)might finally allow us to address these questions. DRL methods have to datebeen applied primarily in the context of games or robotic mechanics, whichoperate under precisely known rules. Here, we demonstrate the ability for DRLalgorithms using deep neural networks to successfully approximate solutions(the "policy function" or control rule) in a non-linear three-variable modelfor a fishery without knowing or ever attempting to infer a model for theprocess itself. We find that the reinforcement learning agent discovers aneffective simplification of the problem to obtain an interpretable controlrule. We show that the policy obtained with DRL is both more profitable andmore sustainable than any constant mortality policy -- the standard family ofpolicies considered in fishery management.

Pretty darn good control: when are approximate solutions better than approximate models