My first experience with deep reinforcement learning
Diego Montoya Sefair

Nice writeup. Did you make a GitHub repository of your experiments?

To me the science is only as good as far as others are able to take your work, verify the results, repeat it, and then perhaps expand upon it. (I haven’t read through the whole thesis yet, so I apologize if that information is in there.)

I think your approach is a good example of how these kinds of ideas should be looked at, in terms of isolating what is and is not effective for the algorithmic learning process.

One clap, two clap, three clap, forty?

By clapping more or less, you can signal to us which stories really stand out.