A code tutorial in Tensorflow that uses Reinforcement Learning to take free kicks. In my previous article, I presented an AI bot trained to play the game of FIFA using Supervised Learning technique. However, the training data required to improve it further quickly became cumbersome to gather and provided little-to-no improvements, making this approach very time consuming. For this sake, I decided to switch to Reinforcement Learning, as suggested by almost everyone who commented on that article! In this article, I'll provide a short description of what Reinforcement Learning is and how I applied it to this game.

As the domestic football season starts to wrap up, all eyes are turning to the World Cup in Russia. EA, unsurprisingly, wants to celebrate the competition with a video game tie-in -- this year, however, it will be released as a free update for FIFA 18. That's in stark contrast to 2014, when EA released a dedicated game for the Xbox 360 and PlayStation 3, and a meagre Ultimate Team expansion for the PS4 and Xbox One. The 2018 FIFA World Cup Russia expansion will include all 32 teams that have qualified for the competition. That includes their players (most of which already exist as part of FIFA 18), national kits and badges.

Game Studios spend millions of dollars and thousands of development hours designing game graphics in trying to make them look as close to reality as possible. While the graphics have looked amazingly realistic in the last few years, it is still easy to distinguish them from the real world. However, with the massive advancements made in the field of image processing using Deep Neural Networks, is it time we can leverage that to improve the graphics while simultaneously also reducing the efforts required to create them? To find out whether the recent developments in deep learning can help me answer my question, I tried to focus on improving the player faces in FIFA using the (in?)famous deepfakes algorithm. It is a Deep Neural Network that can be trained to learn and generate extremely realistic human faces.

Killer Mike and El-P, collectively known as Run the Jewels, are no strangers to video games. Previously they appeared in Gears of War 4 as multiplayer characters, and now the duo are lending their talents to FIFA 18. You can outfit your virtual footballer in kit featuring the group's trademark fist and gun logo on a teal jersey reminiscent of the album art for Run the Jewels 3, and there's also a black variant. More than that, the soundtrack features and exclusive track from the group, "Mean Demeanor." Now, this isn't the first time RTJ has graced a game from EA ("Blockbuster Night Part 2" was in Battlefield: Hardline), but FIFA soundtracks are a bit different, hitting a huge audience around the world.

"To some, Fifa is life." This may sound like hyberbole from the game's creative director Matt Prior, but he has a point. Electronic Arts' football series operates on a scale beyond the dreams of most video game developers. Last year's entry achieved sales of 1.1m in its first week – 300,000 more copies than Adele's 25, the fastest-selling album of all time. For a sizeable number of those 1 million Fifa 17 customers, a big attraction of the game was The Journey, a Mass-Effect-style story mode with branching elements, putting you into the boots of a young pro, Alex Hunter, looking to make it in the Premier League. Unlike anything previously attempted by any football title, it was also successful – Prior says 30 million people worldwide have played it.