Locality-Sensitive Experience Replay for Online Recommendation

TL;DR

This paper introduces a state-aware, locality-sensitive experience replay method for deep reinforcement learning in online recommendation systems, improving training efficiency and recommendation quality amidst complex, dynamic environments.

Contribution

It proposes a novel experience replay model combining locality-sensitive hashing and prioritized sampling to enhance learning in online recommender systems.

Findings

Outperforms existing experience replay methods in simulations

Effectively captures dynamic user preferences

Reduces training time and improves recommendation accuracy

Abstract

Online recommendation requires handling rapidly changing user preferences. Deep reinforcement learning (DRL) is gaining interest as an effective means of capturing users' dynamic interest during interactions with recommender systems. However, it is challenging to train a DRL agent, due to large state space (e.g., user-item rating matrix and user profiles), action space (e.g., candidate items), and sparse rewards. Existing studies encourage the agent to learn from past experience via experience replay (ER). They adapt poorly to the complex environment of online recommender systems and are inefficient in determining an optimal strategy from past experience. To address these issues, we design a novel state-aware experience replay model, which uses locality-sensitive hashing to map high dimensional data into low-dimensional representations and a prioritized reward-driven strategy to replay more valuable experience at a higher chance. Our model can selectively pick the most relevant and salient experiences and recommend the agent with the optimal policy. Experiments on three online simulation platforms demonstrate our model' feasibility and superiority toseveral existing experience replay methods.