# Diversity-Promoting Deep Reinforcement Learning for Interactive Recommendation

arXiv: https://arxiv.org/abs/1903.07826 · HTML: https://mlsanity.com/paper/1903.07826/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Mar 2019.

## Built on by (most cited first, 7 of 7)

- [Initialization Matters: Regularizing Manifold-informed Initialization for Neural Recommendation Systems](https://mlsanity.com/paper/2106.04993/) (2021)
- [Optimizing Novelty of Top-k Recommendations using Large Language Models and Reinforcement Learning](https://mlsanity.com/paper/2406.14169/) (2024)
- [Breaking Information Cocoons: A Hyperbolic Framework for Balancing Exploration and Exploitation in Recommender Systems](https://mlsanity.com/paper/2411.13865/) (2024)
- [Diverse Mini-Batch Selection in Reinforcement Learning for Efficient Chemical Exploration in de novo Drug Design](https://mlsanity.com/paper/2506.21158/) (2025)
- [D2RLIR : an improved and diversified ranking function in interactive recommendation systems based on deep reinforcement learning](https://mlsanity.com/paper/2110.15089/) (2021)
- [Large Language Model-Enhanced Reinforcement Learning for Diverse and Novel Recommendations](https://mlsanity.com/paper/2507.21274/) (2025)
- [Distributional Approximate Nearest Neighbour Search for Uncertainty-Aware Retrieval](https://mlsanity.com/paper/2606.04603/) (2026)

## Abstract (arXiv)

Interactive recommendation that models the explicit interactions between users and the recommender system has attracted a lot of research attentions in recent years. Most previous interactive recommendation systems only focus on optimizing recommendation accuracy while overlooking other important aspects of recommendation quality, such as the diversity of recommendation results. In this paper, we propose a novel recommendation model, named underlineDiversity-promoting underlineDeep underlineReinforcement underlineLearning (D2RL), which encourages the diversity of recommendation results in interaction recommendations. More specifically, we adopt a Determinantal Point Process (DPP) model to generate diverse, while relevant item recommendations. A personalized DPP kernel matrix is maintained for each user, which is constructed from two parts: a fixed similarity matrix capturing item-item similarity, and the relevance of items dynamically learnt through an actor-critic reinforcement learning framework. We performed extensive offline experiments as well as simulated online experiments with real world datasets to demonstrate the effectiveness of the proposed model.