This post is about the Starcraft bot I am developing using machine learning. The project is being developed as part of the "Daj Się Poznać 2017" competition.

This whole week I was wondering what path to take for my bot project. I wanted to use Deeplearning4j, but this library conflicts with BWMirror, which requires Java 32-Bit. An alternative is to rewrite the entire project from BWMirror to JNIBWAPI. The second alternative is to rewrite the project to C++, which I am not very interested in because I don't feel good in this language. I mean, not in Java either, but writing in Java is easier to learn. However, I finally decided to take up TorchCraft. Of course, I lose the opportunity to participate in SSCAIT, but I think it will be better to finally do something related to reinforcement learning using a ready-made environment. If I had to do the same in Java, it would take me a lot of time.

This post is part of my struggle with the book "Reinforcement Learning: An Introduction" by Richard S. Sutton and Andrew G. Barto. Other posts systematizing my knowledge and presenting the code I wrote can be found under the tag Sutton & Barto and in the repository dloranc/reinforcement-learning-an-introduction.

Multi-armed bandit problem (or k-armed bandit problem) is one of the reinforcement learning problems, I don't know if it's the simplest one, but it allows for a relatively quick introduction to the subject and to become familiar with the basic concepts.

This post is about the Starcraft bot I am developing using machine learning. The project is being developed as part of the "Daj Się Poznać 2017" competition.

So far, I have been testing my bot on my computer against the default bot created by Blizzard. It's time to test yourself against other bot creators. I know that instead of the standard bot, you can connect another one using Chaoslauncher - MultiInstance and editing bwapi.ini, but I preferred to see first what the registration procedure in SSCAIT looks like.

This post is about the Starcraft bot I am developing using machine learning. The project is being developed as part of the "Daj Się Poznać 2017" competition.

I spent this week polishing up my Starcraft bot. I didn't want to take up reinforcement learning yet because I preferred to spend my time learning about BWAPI. The code can be viewed here in my repository dloranc/five-pool-bot.

Before we start​

For some time now I have been trying to slowly read the book "Reinforcement Learning: An Introduction" by Richard S. Sutton and Andrew G. Barto. Someone asked for some good RL materials in one of my posts, so I'm sharing and recommending this book. This is supposedly a classic book in this field. In my opinion, it deserves this name, if one can say so after reading less than two chapters of this book.

Recently I was wondering how to implement arguments passed to the script from the command line in Python. You can do this very simply using sys.argv from the standard library:

import sys

if __name__ == '__main__':
	print "\n".join(sys.argv)

This post is about the Starcraft bot I am developing using machine learning. The project is being developed as part of the "Daj Się Poznać 2017" competition.

Since the last post about the project, I've been working on the bot for quite some time, trying to write something that performs some simple strategy. After installing BWAPI, the bot starts and plays with the standard bot included in the game. As I had known the default bot and its weaknesses for years, I decided that my bot would perform a simple strategy called 5 pool with some modifications.

This post is about the Starcraft bot I am developing using machine learning. The project is being developed as part of the "Daj Się Poznać 2017" competition.

Unfortunately, Blizzard and DeepMind failed to create the API and moved the release date to summer this year, which they announced on the Battle.net forum:

We wanted to give you all an update on the progress of the StarCraft II API. Blizzard and DeepMind remain hard at work together defining the API and infrastructure needed to do world class research in StarCraft II. Like many research projects we’ve been learning a lot as we’ve gone along on this new endeavor. We’re eager to get a polished set of tools and documentation into the hands of researchers and developers as soon as possible. Originally we’d hoped to have the API ready by Q1 of this year but think it’s best to shift the official release back to this summer to provide a level of quality and completeness that we know you expect from us.

Usually, training neural networks takes a very long time. Sometimes you need to interrupt the execution of a script when you want to do something else that is equally resource-demanding or turn off the computer. I don't like leaving my PC overnight, so I stop training the neural network and resume training the next day.

This post is about the Starcraft bot I am developing using machine learning. The project is being developed as part of the "Daj Się Poznać 2017" competition.

Every aspiring Starcraft 2 player knows that it is not enough to play to be good. You need, among other things, to analyze your games, as well as the games of other players who are better than you. It would be nice if my bot could do something like that too, at least to a limited extent. I will therefore need replays. Where to get them from? The most common way is to take them from sites like spawningtool.com or ggtracker.com, where they are published by players. Organizers of large tournaments also provide game packs from professional players, but searching the Internet to get these packs does not interest me.