Artificial intelligence (AI) has enabled agents to master complex video games, from first-person shooters likeCounter-Striketo real-time strategy games such asStarCraft IIand racing games likeGran Turismo. While these achievements are notable, applying these AI methods in commercial video game production remains challenging due to computational constraints. In commercial scenarios, the majority of computational resources are allocated to 3D rendering, leaving limited capacity for AI methods, which often demand high computational power, particularly those relying on pixel-based sensors. Moreover, the gaming industry prioritizes creating human-like behavior in AI agents to enhance player experience, unlike academic models that focus on maximizing game performance. This paper introduces a novel methodology for training neural networks via imitation learning to play a complex, commercial-standard, VALORANT-like 2v2 tactical shooter game, requiring only modest CPU hardware during inference. Our approach leverages an innovative, pixel-free perception architecture using a small set of ray-cast sensors, which capture essential spatial information efficiently. These sensors allow AI to perform competently without the computational overhead of traditional methods. Models are trained to mimic human behavior using supervised learning on human trajectory data, resulting in realistic and engaging AI agents. Human evaluation tests confirm that our AI agents provide human-like gameplay experiences while operating efficiently under computational constraints. This offers a significant advancement in AI model development for tactical shooter games and possibly other genres.

Fictitious play is an algorithm for computing Nash equilibria of matrix games. Recently, machine learning variants of fictitious play have been successfully applied to complicated real-world games. This paper presents a simple modification of fictitious play which is a strict improvement over the original: it has the same theoretical worst-case convergence rate, is equally applicable in a machine learning context, and enjoys superior empirical performance. We conduct an extensive comparison of our algorithm with fictitious play, proving an optimal O(1/t) convergence rate for certain classes of games, demonstrating superior performance numerically across a variety of games, and concluding with experiments that extend these algorithms to the setting of deep multiagent reinforcement learning.

This paper describes a machine learning approach to classifying the activities of players in games. Instances of activities generally are not identical because they play out in different contexts, so the challenge is to extract the "essences" of activities from instances. We show how this problem may be mapped to a sequence alignment problem, for which there are polynomial-time solutions. The method works well even when some features of activities are not observable (e.g., the emotional states of players). In fact, these features can in some conditions be inferred with high accuracy.

The task addressed here requires a swarm of mobile robots to monitor a long corridor, i.e., by sweeping through it while avoiding large obstacles such as buildings. In the case of limited sensors and communication, maintaining spatial coverage - especially after passing the obstacles - is a challenging problem. Note that the main objective of this task is coverage. There are two primary methods for agents to achieve coverage: by uniformly increasing the inter-agent distances, and by moving the swarm as a whole. This paper presents a physics-based solution to the task that is based on a kinetic theory approach; our solution achieves both forms of coverage. Furthermore, the paper describes how we transition from our original algorithm to an algorithm utilizing mostly local sensor information, the latter being more realistic for modeling robots. To determine how well our kinetic theory approach performs against a popular alternative controller, experimental comparisons are presented.