A Study of Real-Time Advertising Bidding Based on Reinforcement Learning

Abstract

The purpose of real-time bidding (RTB), which has grown to be a significant component of Internet advertising, is to properly forecast the likelihood of a user clicking on an ad and choose the best bid for that impression. Reinforcement learning (RL) has emerged as a promising approach for RTB bidding strategies due to its ability to learn from feedback and optimize performance over time. This paper surveys RL-based real-time advertising bidding, introduces several main reinforcement learning-based real-time advertising bidding strategies, and explains the advantages of each of these strategies. Furthermore, the author analyzes the current trends and which strategies are combined and why. Overall, this survey sheds light on the potential of RL-based bidding to enhance the effectiveness and efficiency of RTB advertising while also offering information about the current state of the field and future research directions.