I remember reading a comment sometime ago on this site where people on HN seem to have a positive bias towards topics on machine learning and would always upvote it. ML seems to be such a tech buzzword these days. This blog post is at the top of this site, yet there is not a single comment of discussion. I am not trying to sound negative, but rather was wondering if other people shared the same opinion.<p>Regarding the post: This seems like a useful resource. When I read many of these papers, a code supplement makes understanding it so much better. I do a lot of research with RNNs with respect to language modeling and implementing various models when I started researching this field was very useful to get a better understanding. I got great feedback on my implementations where people said it helped them understand.
It's great to see more hacker-friendly introductions to reinforcement learning. Like most facets of machine learning, there are so many interesting applications of reinforcement learning (e.g., we're using RL to optimize email marketing campaigns at Optimail), and we'll only find more as more non-academic hackers discover it.
I find the python code very clear, but I would prefer to see a real life interesting application that doesn't require a lot of computation. In a post in wildml there is an example of using NLP and deep learning for a simple task but after 22 hours of computation the final result is a little disappointing to say the least.<p>I like to read wildml.com and fastml.com blogs, but I would like to find more simple applications that shows real value without using lots of resources. Perhaps there is a subfield of RL where using some kind of proper human intelligence one can hope to beat those giants provided of unlimited computational and financial resources
> but RL is also widely used in Robotics, Image Processing and Natural Language Processing<p>RL for NLP? I would love to know about counter examples, but I'm not aware of a serious project using RL for NLP, let alone 'widely used.' However I do believe RL makes sense for a number of NLP problems.<p>Either way, well done. I appreciate a collection of the algos from Sutton's book (great book), and in Python.