While several high profile video games have served as testbeds for Deep Reinforcement Learning (DRL), this technique has rarely been employed by the game industry for crafting authentic AI behaviors. Previous research focuses on training super-human agents with large models, which is impractical for game studios with limited resources aiming for human-like agents. This paper proposes a sample-efficient DRL method tailored for training and fine-tuning agents in industrial settings such as the video game industry. Our method improves sample efficiency of value-based DRL by leveraging pre-collected data and increasing network plasticity. We evaluate our method training a goalkeeper agent in EA SPORTS FC 25, one of the best-selling football simulations today. Our agent outperforms the game's built-in AI by 10% in ball saving rate. Ablation studies show that our method trains agents 50% faster compared to standard DRL methods. Finally, qualitative evaluation from domain experts indicates that our approach creates more human-like gameplay compared to hand-crafted agents. As a testament to the impact of the approach, the method has been adopted for use in the most recent release of the series.

This paper demonstrates the first application of feedback linearization to replicator dynamics, driving the evolution of non-convergent evolutionary games to systems with guaranteed global asymptotic stability. Replicator dynamics, while a cornerstone of evolutionary game theory, possess neutral stability at Nash equilibria [2], which causes the evolutionary process to oscillate without converging to an optimal strategy. We build a control-theoretic framework that cancels the nonlinear components in replica-tor dynamics, and then apply a linear feedback component to force a strategy change at the Nash equilibrium. Through Lyapunov analysis, we show global convergence from any initial conditions in the probability simplex. We illustrate this approach with a numerical example of a penalty shootout game, where we illustrate that our method guides strategies quickly to mixed Nash equilibria, while the uncontrolled dynamics oscillate. Our work serves as one of the first known connections between nonlinear control theory and evolutionary game dynamics with applications in multi-agent systems, algorithmic trading, and strategic optimization.

Deep learning models trained on more than 1000 penalty kicks in football matches can predict which way the ball will go better than real-life goalkeepers. "Penalty kicks are some of the most decisive moments in soccer, often determining the outcome of major tournaments," says David Freire-Obregón at the University of Las Palmas de Gran Canaria, Spain. "Despite this, real-time support for goalkeepers is still largely intuition-based. We wanted to explore whether machine learning could predict shot direction from a kicker's body motion." So Freire-Obregón and his colleagues scraped 1010 penalty kicks from real, televised matches in Spain.

Cooperative multi-agent reinforcement learning (MARL) under sparse rewards presents a fundamental challenge due to limited exploration and insufficient coordinated attention among agents. In this work, we propose the Focusing Influence Mechanism (FIM), a novel framework that enhances cooperation by directing agent influence toward task-critical elements, referred to as Center of Gravity (CoG) state dimensions, inspired by Clausewitz's military theory. FIM consists of three core components: (1) identifying CoG state dimensions based on their stability under agent behavior, (2) designing counterfactual intrinsic rewards to promote meaningful influence on these dimensions, and (3) encouraging persistent and synchronized focus through eligibility-trace-based credit accumulation. These mechanisms enable agents to induce more targeted and effective state transitions, facilitating robust cooperation even in extremely sparse reward settings. Empirical evaluations across diverse MARL benchmarks demonstrate that the proposed FIM significantly improves cooperative performance compared to baselines.

The FIFA Club World Cup has undergone a revamp since it was last competed in December 2023 in Saudi Arabia. The number of participating clubs has increased fourfold to 32, the frequency of the competition has gone from annual to quadrennial and the champion's prize money – previously 5m – has gone up by a whopping 35m. It's not just the numbers that have changed in the tournament. FIFA is also looking to introduce new technology, including artificial intelligence to help the referees, and it is getting stricter on goalkeepers who waste time while holding the ball. Here's a look at the three big changes to be implemented at the monthlong tournament, which will get under way on Saturday in the United States: Small cameras, protruding from the referees' ears, will capture the live action unfolding in front of them.

Penalties are fraught and game-changing moments in soccer games that teams explicitly prepare for. Consequently, there has been substantial interest in analyzing them in order to provide advice to practitioners. From a data science perspective, such analyses suffer from a significant limitation: they make the unrealistic simplifying assumption that goalkeepers and takers select their action -- where to dive and where to the place the kick -- independently of each other. In reality, the choices that some goalkeepers make depend on the taker's movements and vice-versa. This adds substantial complexity to the problem because not all players have the same action capacities, that is, only some players are capable of basing their decisions on their opponent's movements. However, the small sample sizes on the player level mean that one may have limited insights into a specific opponent's capacities. We address these challenges by developing a player-agnostic simulation framework that can evaluate the efficacy of different goalkeeper strategies. It considers a rich set of choices and incorporates information about a goalkeeper's skills. Our work is grounded in a large dataset of penalties that were annotated by penalty experts and include aspects of both kicker and goalkeeper strategies. We show how our framework can be used to optimize goalkeeper policies in real-world situations.

The integration of artificial intelligence in sports analytics has transformed soccer video understanding, enabling real-time, automated insights into complex game dynamics. Traditional approaches rely on isolated data streams, limiting their effectiveness in capturing the full context of a match. To address this, we introduce SoccerChat, a multimodal conversational AI framework that integrates visual and textual data for enhanced soccer video comprehension. Leveraging the extensive SoccerNet dataset, enriched with jersey color annotations and automatic speech recognition (ASR) transcripts, SoccerChat is fine-tuned on a structured video instruction dataset to facilitate accurate game understanding, event classification, and referee decision making. We benchmark SoccerChat on action classification and referee decision-making tasks, demonstrating its performance in general soccer event comprehension while maintaining competitive accuracy in referee decision making. Our findings highlight the importance of multimodal integration in advancing soccer analytics, paving the way for more interactive and explainable AI-driven sports analysis. https://github.com/simula/SoccerChat

While football analytics has changed the way teams and analysts assess performance, there remains a communication gap between machine learning practice and how coaching staff talk about football. Coaches and practitioners require actionable insights, which are not always provided by models. To bridge this gap, we show how to build wordalizations (a novel approach that leverages large language models) for shots in football. Specifically, we first build an expected goals model using logistic regression. We then use the co-efficients of this regression model to write sentences describing how factors (such as distance, angle and defensive pressure) contribute to the model's prediction. Finally, we use large language models to give an entertaining description of the shot. We describe our approach in a model card and provide an interactive open-source application describing shots in recent tournaments. We discuss how shot wordalisations might aid communication in coaching and football commentary, and give a further example of how the same approach can be applied to other actions in football.

But in recent years, several clubs have brought boffins on board in the hopes of boosting their chances of success. Liverpool has partnered with Google's AI firm DeepMind to advise coaches on corner kicks, while other clubs have hired astrophysicists to analyse data and are even using missile-tracking technology to plot the move of every player. So, can science really tell us how to bend it like Beckham? MailOnline spoke to experts to uncover the formula for the winning football match ahead of Manchester United's match against Liverpool this Sunday. Can science really tell us how to bend it like Beckham? MailOnline spoke to experts to uncover the formula for the winning football match ahead of Manchester United's match against Liverpool this Sunday Taking a penalty is surely the most nerve-wracking experience for any player – a single moment that can decide the result of an entire tournament.

In soccer, it is not uncommon for one team to dominate a match, creating many chances to score but failing to do so, while the opposing team manages to convert one of their few chances into a goal and win the match. Thus, the use of traditional end-of-match statistics is often argued against, because the number of shots, ball possession percentage, and shots inside the opponent's penalty area do not always accurately reflect the outcome of the match. The rapid pace of technological advancements in data collection, storage, and analysis have had a revolutionary impact on soccer analytics over the last decade. Thanks to these advancements, soccer data is collected in two main forms: event data consists of ball-related events and where on the field they occurred such as shots, passes, tackles, and dribbles while tracking data consists of the position of players and the ball throughout play on the pitch. The technological revolution has made it possible to propose a large number of key performance indicators to measure different aspects of the game, such as pass evaluation, quantification of controlled space, shot evaluation, and goal-scoring opportunities using possession values.