Shi, BichenBichenShiTragos, EliasEliasTragosOzsoy, Makbule GulcinMakbule GulcinOzsoyDong, RuihaiRuihaiDongSmyth, BarryBarrySmythHurley, Neil J.Neil J.HurleyLawlor, AonghusAonghusLawlor2021-05-272021-05-272020 Assoc2020-09-26http://hdl.handle.net/10197/12220The 14th ACM Conference on Recommender Systems (RecSys 2020), Online, 22-26 September 2020In this paper we propose DADRL, a distributed, asynchronous reinforcement learning recommender system based on the asynchronous advantage actor-critic model (A3C), which combines ideas from A3C and federated learning (FL). The proposed algorithm keeps the user preferences or interactions on local devices and uses a combination of on-device, local recommendation models and a complementary global model. The global model is trained only by the loss gradients of the local models, rather than directly using user preferences or interactions data. We demonstrate, using well-known datasets and benchmark algorithms, how this approach can deliver performance that is comparable with the current state-of-the-art while enhancing user privacy.en© ACM, 2020. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in RecSys '20: Fourteenth ACM Conference on Recommender Systems http://doi.acm.org/10.1145/3383313Novel personal sensingReinforcement learningRecommender systemsDistributed learningConference Publication10.1145/33833132020-09-03SFI/12/RC/2289_P2https://creativecommons.org/licenses/by-nc-nd/3.0/ie/