ProQuest
Abstract/Details

Inference-Based Personalized Recommendation Via Uncertainty-Aware Dual Actor-Critic Using Reinforcement Learning

Kumar, Shanu.   University of Windsor (Canada) ProQuest Dissertations Publishing,  2023. 30316889.

Abstract (summary)

Ranking of items is the core of an efficient, personalized recommendation system that justifies the overall performance and directly affects the consumer’s experience. For models working on explicit feedback to capture consumers’ satisfaction, nonrated interactions are usually ignored. A large section of users do not provide ratings to items after consuming them hence user satisfaction remains to be discovered for those items and an implicit system that maximizes interaction is utilized in such cases. We aim to extend the application of an explicit system via inference to suggest items to those users so that the users’ satisfaction is considered a pertinent element in the recommendation. Our goal is to use the interaction data of such users to suggest an item that could positively affect them. This work trains the model on explicit data obtained in the same environment. We use a reinforcement learning technique to obtain the model since recommendation can be considered a sequential decision-making task. At the same time, the aim remains long terms cumulative reward maximization by making efficient transitions. Twin actor twin delayed deep deterministic policy gradient is the underlying framework. Our approach considers uncertainty a determining element, which is a significant feature of this work because every user’s behavior in itself is different and uncertain which might be reflected in the data. This can induce uncertainty in the model as there will be insufficient data and the model itself could be inefficient in capturing all the patterns. The final policy, which we refer to as uncertainty-aware dual actor-critic, is acquired via policy aggregation, which is theoretically motivated by the deep ensemble in reinforcement learning with multiple deep deterministic policy gradients. The results of numerous experiments conducted using various benchmark datasets show that our aggregated policy-based approach enhances the recommendation performance by improving the generalization capability of the agent.

Indexing (details)


Business indexing term
Subject
Computer science;
Artificial intelligence
Classification
0984: Computer science
0800: Artificial intelligence
Identifier / keyword
Inference; Actor-critic; Uncertainty; Recommendation systems; Decision-making
Title
Inference-Based Personalized Recommendation Via Uncertainty-Aware Dual Actor-Critic Using Reinforcement Learning
Author
Kumar, Shanu
Number of pages
84
Publication year
2023
Degree date
2023
School code
0115
Source
MAI 84/10(E), Masters Abstracts International
Place of publication
Ann Arbor
Country of publication
United States
ISBN
9798379401689
Advisor
Rueda, Luis
Committee member
Yuan, Xiaobu; Zhang, Ning
University/institution
University of Windsor (Canada)
Department
COMPUTER SCIENCE
University location
Canada -- Ontario, CA
Degree
M.Sc.
Source type
Dissertation or Thesis
Language
English
Document type
Dissertation/Thesis
Dissertation/thesis number
30316889
ProQuest document ID
2795131298
Copyright
Database copyright ProQuest LLC; ProQuest does not claim copyright in the individual underlying works.
Document URL
https://www.proquest.com/pqdtglobal/docview/2795131298