RLRAUC: Reinforcem ent learning based ranking algorithm using user clicks

Derhami, Vali; Paksima, Javad; Khajeh, H.

doi:10.1109/iccke.2014.6993462

Cited by 3 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This algorithm is based on the generalization of the reinforcement learning concepts for learning the ranking functions on graphs. RLRAUC ranking algorithm is based on reinforcement learning with point-wise approach and uses user feedback was proposed by Derhami et al [17]. The main idea behind the proposed method is based on consider value for each single word of query that is able to distinguish between relevant queries.…”

Section: Literature Surveymentioning

confidence: 99%

A Technique for Web Page Ranking by Applying Reinforcement Learning

Deshmukh¹,

S²

2016

International Journal of Advanced Research in Computer and Comm

View full text Add to dashboard Cite

Ranking of site pages is for showing important web pages to client inquiry it is a one of the essential issue in any web search index tool. Today's need is to get significant data to client inquiry. Importance of web pages is depending on interest of users. There are two ranking algorithm is utilized to demonstrate the current raking framework. One is page rank and another is BM25 calculation. Reinforcement learning strategy learns from every connection with dynamic environment. In this paper Reinforcement learning (RL) ranking algorithm is proposed. In this learner is specialist who learns through interactopm with dynamic environment and gets reward of an activity performed. Every site page is considered as a state and fundamental point is to discover score of website page. Score of website pages is identified with number of out connections from current website page .Rank scores in RL rank as considered in recursive way. Along these lines we can enhance outcomes with help of RL method in ranking algorithm.

show abstract

Section: Literature Surveymentioning

confidence: 99%