Presentation: Reinforcement Learning: Not Just for Robots and Games

Reinforcement Learning (RL) and Deep Reinforcement Learning (DRL) has gained huge interests in recent years, as its application in solving very complicated strategy and decision-making problems, including DeepMind's AlphaGo, OpenAI Five, as well as autonomous driving and robotics. Though the technique itself is very powerful and promising, its applications outside of video games, robotics, and simulations are rare. As an "unusual" use case, Jibin will present one of his projects at eBay where the team used RL to improve crawling of targeted web pages. In this talk, we will start from the basics of RL, then to why and how to use it to power the web crawling. This talk is actually "casting a brick to attract jade", hoping to attract more ideas and applications of Reinforcement Learning from more fields.