Filters








44,915 Hits in 5.6 sec

Sequence Adaptation via Reinforcement Learning in Recommender Systems [article]

Stefanos Antaris, Dimitrios Rafailidis
2021 arXiv   pre-print
In addition, we optimize a joint loss function to align the accuracy of the sequential recommendations with the expected cumulative rewards of the critic network, while at the same time we adapt the sequence  ...  To overcome this problem, in this study we propose the SAR model, which not only learns the sequential patterns but also adjusts the sequence length of user-item interactions in a personalized manner.  ...  To overcome the shortcomings of baseline strategies, in this paper we propose a Sequence Adaptation model via deep Reinforcement learning in recommender systems, namely SAR, making the following contributions  ... 
arXiv:2108.01442v1 fatcat:m6f7wm5pzrgkvoumwjpv2b6ls4

Designing and Developing a Novel Hybrid Adaptive Learning Path Recommendation System (ALPRS) for Gamification Mathematics Geometry Course

Chungho Su
2017 Eurasia Journal of Mathematics, Science and Technology Education  
Since recommendation systems possess the advantage of adaptive recommendation, they have gradually been applied to e-learning systems to recommend subsequent learning content for learners.  ...  To overcome this, in the context of a learning style based on an Interpretive Structural Model (ISM), an adaptive learning path recommendation system is proposed comprising: (a) Fuzzy Delphi Method, (b  ...  Most adaptive recommendation systems are applied to business fields, so it is necessary to reinforce recommendation systems for education and learning.  ... 
doi:10.12973/eurasia.2017.01225a fatcat:aaqxdmoqs5debddlzqjhbfzw5i

A Survey on Reinforcement Learning for Recommender Systems [article]

Yuanguo Lin, Yong Liu, Fan Lin, Pengcheng Wu, Wenhua Zeng, Chunyan Miao
2021 arXiv   pre-print
Recently, Reinforcement Learning (RL) based recommender systems have become an emerging research topic.  ...  Nevertheless, there are various challenges of RL when applying in recommender systems.  ...  Applied to the recommender systems, the present study mainly focuses on Multi-Agent Reinforcement Learning (MARL), HRL, and Supervised Reinforcement Learning (SRL).  ... 
arXiv:2109.10665v1 fatcat:whrqgxcb4fa53omquvpy6nitjm

2020 Index IEEE Transactions on Artificial Intelligence Vol. 1

2020 IEEE Transactions on Artificial Intelligence  
., +, TAI Aug. 2020 5-18 Reinforcement learning Fast Real-Time Reinforcement Learning for Partially-Observable Large-Scale Systems.  ...  ., +, TAI Oct. 2020 130-138 R Real-time systems Fast Real-Time Reinforcement Learning for Partially-Observable Large- Scale Systems.  ... 
doi:10.1109/tai.2021.3089904 fatcat:53o6433ljne3lblvr5fuy66lou

Exploring Clustering-Based Reinforcement Learning for Personalized Book Recommendation in Digital Library

Xinhua Wang, Yuchen Wang, Lei Guo, Liancheng Xu, Baozhong Gao, Fangai Liu, Wei Li
2021 Information  
Moreover, due to the the lack of direct supervision information, we treat noise filtering in sequences as a decision-making process and innovatively introduce a reinforcement learning method as our recommendation  ...  As the noisy interactions in students' borrowing sequences may harm the recommendation performance of a book recommender, we focus on refining recommendations via filtering out data noises.  ...  The recommendation system model based on reinforcement learning can better capture the dynamic changes of user interests, and the noise in the sequence can be processed by introducing reinforcement learning  ... 
doi:10.3390/info12050198 doaj:4ac92bb218cf469687cb00f7ad904f24 fatcat:hinnymrc2vc3jo47ipamujw6c4

On Estimating the Training Cost of Conversational Recommendation Systems [article]

Stefanos Antaris, Dimitrios Rafailidis, Mohammad Aliannejadi
2020 arXiv   pre-print
conversational recommendation systems  ...  Conversational recommendation systems have recently gain a lot of attention, as users can continuously interact with the system over multiple conversational turns.  ...  [7] propose an adaptive model to determine the optimal conversational policy based on a reinforcement learning strategy. Christakopoulou et al.  ... 
arXiv:2011.05302v1 fatcat:kr7ua6ipn5fhrgkqdydwe426oe

Constructing evidence-based treatment strategies using methods from computer science

Joelle Pineau, Marc G. Bellemare, A. John Rush, Adrian Ghizaru, Susan A. Murphy
2007 Drug and Alcohol Dependence  
The instance-based reinforcement learning methodology comes from the computer science literature, where it was developed to optimize sequences of actions in an evolving, time varying system.  ...  This paper details a new methodology, instance-based reinforcement learning, for constructing adaptive treatment strategies from randomized trials.  ...  Acknowledgements We gratefully acknowledge the contribution of the STAR*D team, in particular investigators at the Texas Southwestern Medical Center and the University of Pittsburgh School of Public Health  ... 
doi:10.1016/j.drugalcdep.2007.01.005 pmid:17320311 pmcid:PMC1934348 fatcat:53ya6tfhmfhhvkt7urskg6wuie

Natural Language Generation as Planning under Uncertainty Using Reinforcement Learning [article]

Verena Rieser, Oliver Lemon
2016 arXiv   pre-print
We then train a NLG pol- icy using Reinforcement Learning (RL), which adapts its behaviour to noisy feed- back from the current generation context.  ...  We present and evaluate a new model for Natural Language Generation (NLG) in Spoken Dialogue Systems, based on statistical planning, given noisy feedback from the current generation context (e.g. a user  ...  We used this regression model to set weights in a reward function for Reinforcement Learning, and so optimise a context-adaptive presentation policy.  ... 
arXiv:1606.04686v1 fatcat:ujcx27wfn5eotfloksqmwvxt3q

DESIGNING A HOLISTIC ADAPTIVE RECOMMENDER SYSTEM (HARS) FOR CUSTOMER RELATIONSHIP DEVELOPMENT: A CONCEPTUAL FRAMEWORK

Alina Popa, Bucharest Academy of Economic Studies
2021 Journal of Social Sciences  
In this paper, it is proposed a novel Reinforcement Learning-based recommender system that has an integrative view over data and recommendation landscape, as well as it is highly adaptive to changes in  ...  customer behavior, the Holistic Adaptive Recommender System (HARS).  ...  One of the best-known approaches that allows to include adaptability in a system is Reinforcement Learning (RL) [15 -17] , being used successfully in robotics for changing environments [18] , sustainable  ... 
doi:10.52326/jss.utm.2021.4(2).09 fatcat:7mt2wynp4be4jg26ozd6hbzm5a

Natural Language Generation as Planning under Uncertainty for Spoken Dialogue Systems [chapter]

Verena Rieser, Oliver Lemon
2010 Lecture Notes in Computer Science  
We then train a NLG policy using Reinforcement Learning (RL), which adapts its behaviour to noisy feedback from the current generation context.  ...  We present and evaluate a new model for Natural Language Generation (NLG) in Spoken Dialogue Systems, based on statistical planning, given noisy feedback from the current generation context (e.g. a user  ...  We used this regression model to set weights in a reward function for Reinforcement Learning, and so optimise a context-adaptive presentation policy.  ... 
doi:10.1007/978-3-642-15573-4_6 fatcat:tb6fmuwasjd3tgkg3b3ccbgzmu

Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning

Xiangyu Zhao, Liang Zhang, Zhuoye Ding, Long Xia, Jiliang Tang, Dawei Yin
2018 Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining - KDD '18  
We model the sequential interactions between users and a recommender system as a Markov Decision Process (MDP) and leverage Reinforcement Learning (RL) to automatically learn the optimal strategies via  ...  In this paper, we develop a novel approach to incorporate them into the proposed deep recommender system (DEERS) framework.  ...  ACKNOWLEDGEMENTS This material is based upon work supported by, or in part by, the National Science Foundation (NSF) under grant number IIS-1714741 and IIS-1715940.  ... 
doi:10.1145/3219819.3219886 dblp:conf/kdd/ZhaoZDXTY18 fatcat:gwk6s6jxnzfnrgg762b6gmz67i

Customizing treatment to the patient: Adaptive treatment strategies

Susan A. Murphy, L.M. Collins, A. John Rush
2007 Drug and Alcohol Dependence  
Each individual is provided a sequence of adapted variations in treatment, adapted mainly via the number and type of assigned counseling sessions.  ...  These strategies individualize treatment via decision rules that recommend when and for whom the treatment should change; frequently they incorporate a sequence of treatments.  ... 
doi:10.1016/j.drugalcdep.2007.02.001 pmid:17350181 pmcid:PMC1924645 fatcat:bv3edfu47zdldf7g5przaoktia

Learning teaching strategies in an Adaptive and Intelligent Educational System through Reinforcement Learning

Ana Iglesias, Paloma Martínez, Ricardo Aler, Fernando Fernández
2008 Applied intelligence (Boston)  
This paper proposes to use Reinforcement Learning (RL) in the pedagogical module of an educational system so that the system learns automatically which is the best pedagogical policy for teaching students  ...  One of the most important issues in Adaptive and Intelligent Educational Systems (AIES) is to define effective pedagogical policies for tutoring students according to their needs.  ...  Reinforcement learning deals with agents connected to their environment via perception and action.  ... 
doi:10.1007/s10489-008-0115-1 fatcat:er6j5c7btzftjmi3vupwewyoqy

Sequential Recommendation with Adaptive Preference Disentanglement [article]

Weiqi Shao, Xu Chen, Jiashu Zhao, Long Xia, Dawei Yin
2021 arXiv   pre-print
In particular, we regard the disentanglement of user preference as a Markov decision process, and design a reinforcement learning method to implement the behavior allocator.  ...  To make the disentangled sub-sequences not too sparse, we introduce a curriculum reward, which adaptively penalizes the action of creating a new sub-sequence.  ...  sub- reinforcement learning based allocator agent 𝜋, aiming to disentan- sequences number.  ... 
arXiv:2112.02812v1 fatcat:cp4kvsgrgnbxzfnof4zgjvenym

Fairness Embedded Adaptive Recommender System: A Conceptual Framework

Alina Popa
2021 International Journal of Advanced Computer Science and Applications  
In this paper, it is proposed a novel Reinforcement Learning-based recommender system that is highly adaptive to changes in customer behavior and focuses on ensuring both producer and consumer fairness  ...  , Fairness Embedded Adaptive Recommender System (FEARS).  ...  One of the best-known approaches that allows to include adaptability in a system is Reinforcement Learning (RL) [7] [8] [9] .  ... 
doi:10.14569/ijacsa.2021.0120560 fatcat:ndmedxnjcfgtnoyjth6muzidre
« Previous Showing results 1 — 15 out of 44,915 results