That's very interesting case. In my company, we would also like to optimize email marketing campaign using RL. However, based on my little experience using RL, (please correct me if I'm wrong) wouldn't it take long to iterate and update the V and policy function (or Q function if we use Q-learning), so I'm a bit skeptical if it can be used for real world case where we need to wait days to get the email response as feedback from the environment.
Great points. It's definitely more challenging than learning to play a simple arcade game or something, where feedback is invariant and often instantaneous. To address these challenges, we use a combination of (1) heuristics tailoring our RL algorithms to the problem at hand, (2) many converging sources of feedback. Most importantly, as with any machine learning implementation, it works in practice — our AI-driven campaigns beat randomized, control conditions!
Anybody have tried this algorithm compared to simpler strategy, like average of word vector, for document classification task? Or compared to using skipthought sent2vec pre-trained model?
I have tried both some time ago for an OCR task. In my brief experience, GCV performs better than Microsoft. Also last time I tried, I sometimes randomly get server error from Microsoft, so I guess Google infrastructure is more ready. The downside is GCV is a bit pricier. Also both do not provide parameter to set language models, so that's a minus in my eyes.
