Partially Observable Markov Decision Process for Recommender Systems

By Zhongqi Lu, Qiang Yang. 2016

30 citations recorded by the source corpus.

We report the "Recurrent Deterioration" (RD) phenomenon observed in online recommender systems. The RD phenomenon is reflected by the trend of performance degradation when the recommendation model is always trained based on users' feedbacks of the previous recommendations. There are several reasons for the recommender systems to encounter the RD phenomenon, including the lack of negative training data and the evolution of users' interests, etc. Motivated to tackle the problems causing the RD phenomenon, we propose the POMDP-Rec framework, which is a neural-optimized Partially Observable Markov Decision Process algorithm for recommender systems. We show that the POMDP-Rec framework effectively uses the accumulated historical data from real-world recommender systems and automatically achieves comparable results with those models fine-tuned exhaustively by domain exports on public datasets.

Subfields: Artificial Intelligence, Information Systems, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Management Science and Operations Research

Citations in the corpus

DRN: A Deep Reinforcement Learning Framework for News Recommendation (2018, background): “[26, 27, 35, 36, 38] try to model the item or n-gram of items as state (or observation in Partially Observed MDP), and the transition between items (recommendation for the next item) as the action.”
Reinforcement Learning based Recommender Systems: A Survey (2021, methodology): “This algorithm has been used by several RLRSs [90, 91, 94, 95].”