![]() First of all “one-armed bandit” is 100-year-old slang, and second, the image of a slot machine with multiple arms to pull is a weird one. One popular way to model problems for RL algorithms is as a “ multi-armed bandit”, but I have always thought the term was unnecessarily difficult, considering it's supposed to be a helpful metaphor. Reinforcement learning is providing a huge boost to many applications, in particular in e-commerce for exploring and anticipating customer behaviour, including where I work as a data scientist, Wayfair. ![]()
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |