Contrasting Impact of Start State on Performance of AReinforcement Learning Recommender System

Abstract

A recommendation problem and RL problem are very similar, as both try to increase user satisfaction in a certain environment. Typical recommender systems mainly rely on history of the user to give future recommendations and doesn’t adapt well to current changing user demands. RL can be used to evolve with currently changing user demands by considering a reward function as feedback. In this paper, recommendation problem is modeled as an RL problem using a squared grid environment, with each grid cell representing a unique state generated by a biclustering algorithm Bibit. These biclusters are sorted according to their overlapping and then mapped to a squared grid. An RL agent then moves on this grid to obtain recommendations. However, the agent has to decide the most pertinent start state that can give best recommendations. To decide the start state of the agent, a contrasting impact of different start states on the performance of RL agent-based RSs is required. For this purpose, we applied seven different similarity measures to determine the start state of the RL agent. These similarity measures are diverse, attributed to the fact that some may not use rating values, some may only use rating values, or some may use global parameters like average rating value or standard deviation in rating values. Evaluation is performed on ML-100K and FilmTrust datasets under different environment settings. Results proved that careful selection of start state can greatly improve the performance of RL-based recommender systems,

Authors and Affiliations

Sidra Hassan, Mubbashir Ayub, Muhammad Waqar, Tasawer Khan

Keywords

Related Articles

Performance Evaluation of Fuzzy Logic-BasedRPL Objective Functions

Introduction: This paper is based on the evaluation of different fuzzy logic-based approaches, implemented by Routing Protocol for Low-power Lossy networks (RPL), carried out using different topologies. Importance: Th...

AI-Powered Classification for Cheating Detection in Offline Examinations Using Deep Learning Techniques with CUI Dataset

Supervising students during examinations is a very demanding process, and real-time supervision by human proctors proves to be challenging. This method is time-consuming and involves the extra work of monitoring severa...

Delving into the Practices Involved in the Creation and Dissemination of Misinformation

This study investigates the authenticity of news with specific training features validating the same with specific machine-learning techniques. The contents of fake news are created to make credible information that wo...

Lightweight Cryptography Algorithms for Internet of ThingsEnabled Networks.A Comparative Study

The rapid advancement of technology has facilitated the interconnection of numerous devices, enabling the collection of vast amounts of data. Consequently, ensuring security within IoT networks has become a top priorit...

Computational Analysisof ModelHousesof Da Kali KORin Matta Swat

Natural disasters such as floods and earthquakes, exacerbated by global warming and environmental degradation, pose significant challenges for modern architecture. This study critically evaluates a rural residential ho...

Download PDF file
  • EP ID EP760327
  • DOI -
  • Views 17
  • Downloads 0

How To Cite

Sidra Hassan, Mubbashir Ayub, Muhammad Waqar, Tasawer Khan (2024). Contrasting Impact of Start State on Performance of AReinforcement Learning Recommender System. International Journal of Innovations in Science and Technology, 6(2), -. https://europub.co.uk/articles/-A-760327