![]() ![]() There is no reward function, so we need to develop it. We can also tell the rocket what to do by sending actions. We receive states as arrays so we can easily work on them. We used Python, but mod is available for other languages (C-nano, C++, C#, Java, Lua). Thanks to this mod we can control our rocket via already created unofficial library. kRPC creates a server, by which we can send and receive messages from the environment. You just need to download the mod and paste kRPC folder to GameData directory. There is a great community of KSP players, which thanks to them as well as kRPC mod connecting to game was pretty easy. Of course it brought us a lot of joy, but there were many challenges which we had to face. ![]() We have choosen the Kerbal Space Program, because Open AI dropped bringing AI to this game and it sounded like so much fun. We wanted to gain experience with reinforcement learning for our next commercial project at Whiteaster., so we started a small R&D project. if know_the_basics_of_RL: read(this_article) You can learn more from /docsīasically the goal of reinforcement learning is to find a sequence of actions from some states, which are received from environment that lead to bigger reward. It is a good starting point for the beginning your journey with reinforcement learning. You have probably heard of the Open AI Gym. They’ve created easier environments based mostly on Atari games. Project was called Universe, but it was abandoned a year ago.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |