|Applying Reinforcement Learning to Develop Game AI in Netease Games
|Track / Format:
Did you know free users get access to 30% of content from the last 2 years?
|This session introduces the application of reinforcement learning in NetEase Games, including the problems encountered in the development, the tried solutions and the final results. It not only gives some advice, but also provides several tools, a series of solutions and a set of development process specifications for game developers to overcome difficulties when using this kind of technology. In NetEase Games, reinforcement learning demonstrates its ability to allow game designers to develop more intelligent, human-like AI. The results in real online games show that it has surpassed the original behavioral tree AI in some aspects and won unanimous praise from the project team and game players.