Generative Adversarial Networks (GANs) can generate levels for a variety of games. This paper focuses on combining GAN-generated segments in a snaking pattern to create levels for Mega Man. Adjacent segments in such levels can be orthogonally adjacent in any direction, meaning that an otherwise fine segment might impose a barrier between its neighbor depending on what sorts of segments in the training set are being most closely emulated: horizontal, vertical, or corner segments. To pick appropriate segments, multiple GANs were trained on different types of segments to ensure better flow between segments. Flow was further improved by evolving the latent vectors for the segments being joined in the level to maximize the length of the level's solution path. Using multiple GANs to represent different types of segments results in significantly longer solution paths than using one GAN for all segment types, and a human subject study verifies that these levels are more fun and have more human-like design than levels produced by one GAN.

Game studios and enthusiasts may soon have a new tool at their disposal to speed up game development and experiment with different styles of play. Georgia Institute of Technology researchers have developed a new approach using an artificial intelligence to learn a complete game engine, the basic software of a game that governs everything from character movement to rendering graphics. Their AI system watches less than two minutes of gameplay video and then builds its own model of how the game operates by studying the frames and making predictions of future events, such as what path a character will choose or how enemies might react. To get their AI agent to create an accurate predictive model that could account for all the physics of a 2D platform-style game, the team trained the AI on a single "speedrunner" video, where a player heads straight for the goal. This made "the training problem for the AI as difficult as possible."

Unfortunately, I didn't really get to do any exploration, but I did get a good taste of the smooth and fluid combat system during my demo. One trigger locks you on to your enemies and the other lets you blast away, making it relatively painless to keep up with the swarms of fast-moving attacking robots. Another button tells your robot companion to attack, and you can swap rapidly between them at any time. Each bot has its own special attack you can use to even the odds, as well. The bots are designed to be crucial to your success -- if you forget about utilizing those special attacks, you'll likely end up in big trouble.

If imitation is the sincerest form of flattery, Sony and Microsoft may be a bit embarrassed by Tuesday's reveal by China's Fuze Entertainment. The Fuze Tomahawk F1 is an Android-based game console that features the design of the PS4 hardware along with a controller that's eerily reminiscent of the Xbox One wireless controller. The console's operating system also bears a striking resemblance to the PlayStation Network. Fuze Entertainment is a new venture formed by former employees of Tencent, Huawei and Nvidia, according the ZhugeEX blog. In China, cheaper Android-based mini-systems that are designed to be family-centric entertainment machines capable of streaming TV shows or playing games is preferred over dedicated game systems in the burgeoning console market.