Learning Reinforcement Learning, with Code, Exercises, and Solutions

Re:Learning Reinforcement Learning, with Code, Exercises, an... by dennybritz on Sunday October 02, 2016 @01:49PM (#12623447)

Another reason may be that this is a pure "resource" post that doesn't make an argument or represents personal opinions that people could easily comment on. It's not a good basis to start a discussion, unlike many other HN posts.

However, I'd appreciate more comments of course ;)

[ Parent | on HN ]

Re:Learning Reinforcement Learning, with Code, Exercises, an... by joanderson on Sunday October 02, 2016 @01:59PM (#12623476)

I guess you raise a good point since it is only a "resource" post. My comment was geared toward all ML related posts in general.

I do research in ML so I love seeing these posts, but the fact that words like neural networks has become such a buzzword is somewhat disappointing. I remember all the buzz when Swiftkey released their "neural network" keyboard simply because of the name.

[ Parent | on HN ]

Re:Learning Reinforcement Learning, with Code, Exercises, an... by coredog64 on Monday October 03, 2016 @10:20AM (#12627584)

More than a few times I've seen a resource post like this that has garnered discussion on the usefulness of what was being done. In a few extreme cases, HN has exposed people copy/pasting the work of others and linked to the originals.

[ Parent | on HN ]