There has been a growing interest in using AI to model human behavior, particularly in domains where humans interact with this technology. While most existing work models human behavior at an aggregate level, our goal is to model behavior at the individual level. Recent approaches to behavioral stylometry -- or the task of identifying a person from their actions alone -- have shown promise in domains like chess, but these approaches are either not scalable (e.g., fine-tune a separate model for each person) or not generative, in that they cannot generate actions. We address these limitations by framing behavioral stylometry as a multi-task learning problem -- where each task represents a distinct person -- and use parameter-efficient fine-tuning (PEFT) methods to learn an explicit style vector for each person. Style vectors are generative: they selectively activate shared "skill" parameters to generate actions in the style of each person. They also induce a latent space that we can interpret and manipulate algorithmically. In particular, we develop a general technique for style steering that allows us to steer a player's style vector towards a desired property. We apply our approach to two very different games, at unprecedented scales: chess (47,864 players) and Rocket League (2,000 players). We also show generality beyond gaming by applying our method to image generation, where we learn style vectors for 10,177 celebrities and use these vectors to steer their images.

News that GOG.com has delisted 29 games this month is a sobering reminder that at any moment the games you own could vanish from your PC game libraries at any time and there's not much you can do about it. Admittedly, GOG's games include titles that many gamers may not have heard about. But history has shown that this happens to well-known titles too and on platforms with millions of users like Steam and Origin. So how is it that something you've legitimately bought can be whipped away in a heartbeat? Don't we have consumer protection laws against that?

A successful tactic that is followed by the scientific community for advancing AI is to treat games as problems, which has been proven to lead to various breakthroughs. We adapt this strategy in order to study Rocket League, a widely popular but rather under-explored 3D multiplayer video game with a distinct physics engine and complex dynamics that pose a significant challenge in developing efficient and high-performance game-playing agents. In this paper, we present Lucy-SKG, a Reinforcement Learning-based model that learned how to play Rocket League in a sample-efficient manner, outperforming by a notable margin the two highest-ranking bots in this game, namely Necto (2022 bot champion) and its successor Nexto, thus becoming a state-of-the-art agent. Our contributions include: a) the development of a reward analysis and visualization library, b) novel parameterizable reward shape functions that capture the utility of complex reward types via our proposed Kinesthetic Reward Combination (KRC) technique, and c) design of auxiliary neural architectures for training on reward prediction and state representation tasks in an on-policy fashion for enhanced efficiency in learning speed and performance. By performing thorough ablation studies for each component of Lucy-SKG, we showed their independent effectiveness in overall performance. In doing so, we demonstrate the prospects and challenges of using sample-efficient Reinforcement Learning techniques for controlling complex dynamical systems under competitive team-based multiplayer conditions.

Artificial intelligence has already beaten chess. Hell, the most sophisticated AI systems have a very good chance against top players in the incredibly complicated game of Go. But, in the uber-complicated car-based soccer game of Rocket League, can an AI do a boosted 360 aerial bicycle kick power shot from the midline? Can it pinch a ball off the side ramp so precisely it sails into the goal at 90 MPH? No, at least not yet, but AI can apparently dribble like a madman. For more than a week, players have been driven up the wall (sometimes literally, in game) by machine learning-based AI that's been hacked into games of Rocket League.

Last week, Reed Wilen, an elite gamer who uses the handle "Chicago" in Rocket League, a popular vehicular-soccer game, encountered a strange and troubling new opponent. The player seemed like a novice at first, moving their rocket-powered vehicle in a hesitant and awkward way. Then they caught and balanced the ball perfectly on the hood of their car, and dribbled it with superhuman skill towards the goal at high speed. Not only was the other driver clearly a bot--it was also ridiculously good. "It is very confusing to play against," Wilen says.

Research in the field of machine learning and AI, now a key technology in practically every industry and company, is far too voluminous for anyone to read it all. This column, Perceptron (previously Deep Science), aims to collect some of the most relevant recent discoveries and papers -- particularly in, but not limited to, artificial intelligence -- and explain why they matter. This week in AI, researchers discovered a method that could allow adversaries to track the movements of remotely-controlled robots even when the robots' communications are encrypted end-to-end. The coauthors, who hail from the University of Strathclyde in Glasgow, said that their study shows adopting the best cybersecurity practices isn't enough to stop attacks on autonomous systems. Remote control, or teleoperation, promises to enable operators to guide one or several robots from afar in a range of environments.

AI is rapidly changing the face of traditional games and sports. Whose side are you on? He sees an opening on the left flank and immediately punishes them. After rushing to the side, he finds his teammates in the center and quickly crosses for the finish! Turn on any sports channel and you'll hear something similar. Chances are you've imagined Ronaldo or another star player running down a new pitch.

If you thought it was just a matter of time before Psyonix synced up with its parent company Epic Games by adding battle royale to Rocket League... your beliefs were well-founded. Psyonix is introducing a limited-time Knockout Bash mode that drops the usual vehicular soccer in favor of battle royale's familiar last-one-standing mechanic. Eight players try to survive by attacking each other and staying inside an ever-shrinking "Safezone." That will sound more than a little familiar to Fortnite fans, but Rocket League's take includes a few important twists. Players only leave after they've been knocked out three times, for instance.

On Feb. 2, "Rocket League" introduced a new limited-time football mode, a tie-in to the Super Bowl. The format pits teams of four against each other in a loose approximation of football. Touching the football results in it being mounted on your car's roof; teammates can go for handoffs, while opponents will endeavor to knock the ball out of your grasp. Jumping twice passes the ball forward, allowing for more complex plays. If you manage to drive the ball into the goal, that will net your team 7 points; players are awarded 3 points for passing it in.

With this change, the five-year-old vehicular soccer game will join a growing catalog of free-to-play titles under Epic Games, the creators of Fortnite and the parent company behind Rocket League. The decision to ensure Rocket League is not just on every platform but also free for everyone mirrors the wildly successful formula Epic concocted for Fortnite, which is now a cultural phenomenon played by a generation of gamers.