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

Many real-world systems problems require reasoning about the long termconsequences of actions taken to configure and manage the system. Theseproblems with delayed and often sequentially aggregated reward, are ofteninherently reinforcement learning problems and present the opportunity toleverage the recent substantial advances in deep reinforcement learning.However, in some cases, it is not clear why deep reinforcement learning is agood fit for the problem. Sometimes, it does not perform better than thestate-of-the-art solutions. And in other cases, random search or greedyalgorithms could outperform deep reinforcement learning. In this paper, wereview, discuss, and evaluate the recent trends of using deep reinforcementlearning in system optimization. We propose a set of essential metrics to guidefuture works in evaluating the efficacy of using deep reinforcement learning insystem optimization. Our evaluation includes challenges, the types of problems,their formulation in the deep reinforcement learning setting, embedding, themodel used, efficiency, and robustness. We conclude with a discussion on openchallenges and potential directions for pushing further the integration ofreinforcement learning in system optimization.

A View on Deep Reinforcement Learning in System Optimization