Blog(1)

• Off-Policy Selection for Optimizing Ad Display Timing in Mobile Games (Samsung Instant Plays)

  Off-Policy Selection (OPS) aims to select the best policy from a set of policies trained using offline Reinforcement Learning. In this work, we describe our custom OPS method and its successful application in Samsung Instant Plays for optimizing ad delivery timings.

Research Areas(0)

Publications(3)

• PDMFRec: A Decentralised Matrix Factorisation with Tunable User-centric Privacy

  AuthorErika Duriakova, Elias Z. Tragos, Barry Smyth, Neil Hurley, Francisco J. Peña, Panagiotis Symeonidis, James Geraci, Aonghus Lawlor

  PublishedACM Conference on Recommender Systems (RecSys)

  Date2019-09-16

• PyRecGym: A Reinforcement Learning Gym for Recommender Systems

  AuthorBichen Shi, Makbule Gulcin Ozsoy, Neil Hurley, Barry Smyth, Elias Z. Tragos, James Geraci, Aonghus Lawlor

  PublishedACM Conference on Recommender Systems (RecSys)

  Date2019-09-16

• Interactive Recommendation via Deep Neural Memory Augmented Reinforcement Learning

  AuthorYilin Shen, Yue Deng, Avik Ray, Hongxia Jin

  PublishedACM Conference on Recommender Systems (RecSys)

  Date2018-10-02

News(0)

Others(0)