Enhancing Prediction Models with Reinforcement Learning

2024-11-21 · Karol Radziszewski, Piotr Ociepka

We present a large-scale news recommendation system implemented at Ringier Axel Springer Polska, focusing on enhancing prediction models with reinforcement learning techniques. The system, named Aureus, integrates a variety of algorithms, including multi-armed bandit methods and deep learning models based on large language models (LLMs). We detail the architecture and implementation of Aureus, emphasizing the significant improvements in online metrics achieved by combining ranking prediction models with reinforcement learning. The paper further explores the impact of different models mixing on key business performance indicators. Our approach effectively balances the need for personalized recommendations with the ability to adapt to rapidly changing news content, addressing common challenges such as the cold start problem and content freshness. The results of online evaluation demonstrate the effectiveness of the proposed system in a real-world production environment.

📄 PDF Abstract BibTeX arXiv:2412.06791

Code (0)

등록된 구현이 없습니다.

Tasks

News RecommendationPrediction reinforcement-learning Reinforcement Learning

Enhancing Molecular Design through Graph-based Topological Reinforcement Learning

2024-11-22 · Xiangyu Zhang

The generation of drug-like molecules is crucial for drug design. Existing reinforcement learning (RL) methods often overlook structural information. However, feature engineering-based methods usually merely focus on bin…

Drug Design Drug Discovery Feature Engineering Prediction+3

STEMO: Early Spatio-temporal Forecasting with Multi-Objective Reinforcement Learning

2024-06-06 · Wei Shao, Yufan Kang, Ziyan Peng, Xiao Xiao 외

Accuracy and timeliness are indeed often conflicting goals in prediction tasks. Premature predictions may yield a higher rate of false alarms, whereas delaying predictions to gather more information can render them too l…

Multi-Objective Reinforcement Learning reinforcement-learning Reinforcement Learning Spatio-Temporal Forecasting

Interpretable Rationale Augmented Charge Prediction System

2018-08-01 · COLING 2018 8 · Xin Jiang, Hai Ye, Zhunchen Luo, Wenhan Chao 외

This paper proposes a neural based system to solve the essential interpretability problem existing in text classification, especially in charge prediction task. First, we use a deep reinforcement learning method to extra…

Classification Deep Reinforcement Learning General Classification Prediction+5

PreND: Enhancing Intrinsic Motivation in Reinforcement Learning through Pre-trained Network Distillation

2024-10-02 · Mohammadamin Davoodabadi, Negin Hashemi Dijujin, Mahdieh Soleymani Baghshah

Intrinsic motivation, inspired by the psychology of developmental learning in infants, stimulates exploration in agents without relying solely on sparse external rewards. Existing methods in reinforcement learning like R…

Developmental Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

RLVR-World: Training World Models with Reinforcement Learning

2025-05-20 · Jialong Wu, Shaofeng Yin, Ningya Feng, Mingsheng Long

World models predict state transitions in response to actions and are increasingly developed across diverse modalities. However, standard training objectives such as maximum likelihood estimation (MLE) often misalign wit…

reinforcement-learning Reinforcement Learning Robot Manipulation