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

In many reinforcement learning (RL) problems, it takes some time until ataken action by the agent reaches its maximum effect on the environment andconsequently the agent receives the reward corresponding to that action by adelay called action-effect delay. Such delays reduce the performance of thelearning algorithm and increase the computational costs, as the reinforcementlearning agent values the immediate rewards more than the future reward that ismore related to the taken action. This paper addresses this issue byintroducing an applicable enhanced Q-learning method in which at the beginningof the learning phase, the agent takes a single action and builds a functionthat reflects the environments response to that action, called the reflexive$\gamma$ - function. During the training phase, the agent utilizes the createdreflexive $\gamma$- function to update the Q-values. We have applied thedeveloped method to a structural control problem in which the goal of the agentis to reduce the vibrations of a building subjected to earthquake excitationswith a specified delay. Seismic control problems are considered as a complextask in structural engineering because of the stochastic and unpredictablenature of earthquakes and the complex behavior of the structure. Threescenarios are presented to study the effects of zero, medium, and longaction-effect delays and the performance of the Enhanced method is compared tothe standard Q-learning method. Both RL methods use neural network to learn toestimate the state-action value function that is used to control the structure.The results show that the enhanced method significantly outperforms theperformance of the original method in all cases, and also improves thestability of the algorithm in dealing with action-effect delays.

Enhancing reinforcement learning by a finite reward response filter with a case study in intelligent structural control