Humanoid soccer dribbling is a highly challenging task that demands dexterous ball manipulation while maintaining dynamic balance. Traditional rule-based methods often struggle to achieve accurate ball control due to their reliance on fixed walking patterns and limited adaptability to real-time ball dynamics. To address these challenges, we propose a two-stage curriculum learning framework that enables a humanoid robot to acquire dribbling skills without explicit dynamics or predefined trajectories. In the first stage, the robot learns basic locomotion skills; in the second stage, we fine-tune the policy for agile dribbling maneuvers. We further introduce a virtual camera model in simulation that simulates the field of view and perception constraints of the real robot, enabling realistic ball perception during training. We also design heuristic rewards to encourage active sensing, promoting a broader visual range for continuous ball perception. The policy is trained in simulation and successfully transferred to a physical humanoid robot. Experiment results demonstrate that our method enables effective ball manipulation, achieving flexible and visually appealing dribbling behaviors across multiple environments. This work highlights the potential of reinforcement learning in developing agile humanoid soccer robots. Additional details and videos are available at https://zhuoheng0910.github.io/dribble-master/.

Reasoning models leveraging long chains of thought employ various cognitive skills, such as verification of their answers, backtracking, retrying by an alternate method, and more. Previous work has shown that when a base language model exhibits these skills, training that model further with reinforcement learning (RL) can learn to leverage them. How can we get models to leverage skills that aren't exhibited by base models? Our work, SkillFactory, is a method for fine-tuning models to roughly learn these skills during a supervised fine-tuning (SFT) stage prior to RL. Our approach does not rely on distillation from a stronger model, but instead uses samples from the model itself, rearranged to provide training data in the format of those skills. These "silver" SFT traces may be imperfect, but are nevertheless effective for priming a model to acquire skills during RL. Our evaluation shows that (1) starting from SkillFactory SFT initialization helps a model to generalize to harder variants of a task post-RL, despite lower performance pre-RL; (2) cognitive skills are indeed used by the model; (3) RLed SkillFactory models are more robust to regression on out-of-domain tasks than RLed base models. Our work suggests that inductive biases learned prior to RL help models learn robust cognitive skill use.

Soccer video understanding has motivated the creation of datasets for tasks such as temporal action localization, spatiotemporal action detection (STAD), or multiobject tracking (MOT). The annotation of structured sequences of events (who does what, when, and where) used for soccer analytics requires a holistic approach that integrates both STAD and MOT. However, current action recognition methods remain insufficient for constructing reliable play-by-play data and are typically used to assist rather than fully automate annotation. Parallel research has advanced tactical modeling, trajectory forecasting, and performance analysis, all grounded in game-state and play-by-play data. This motivates leveraging tactical knowledge as a prior to support computer-vision-based predictions, enabling more automated and reliable extraction of play-by-play data. We introduce Footovision Play-by-Play Action Spotting in Soccer Dataset (FOOTPASS), the first benchmark for play-by-play action spotting over entire soccer matches in a multi-modal, multi-agent tactical context. It enables the development of methods for player-centric action spotting that exploit both outputs from computer-vision tasks (e.g., tracking, identification) and prior knowledge of soccer, including its tactical regularities over long time horizons, to generate reliable play-by-play data streams. These streams form an essential input for data-driven sports analytics.

Recent advances in agent development have focused on scaling model size and raw interaction data, mirroring successes in large language models. However, for complex, long-horizon multi-agent tasks such as robotic soccer, this end-to-end approach often fails due to intractable exploration spaces and sparse rewards. We propose that an effective world model for decision-making must model the world's physics and also its task semantics. A systematic review of 2024 research in low-resource multi-agent soccer reveals a clear trend towards integrating symbolic and hierarchical methods, such as Hierarchical Task Networks (HTNs) and Bayesian Strategy Networks (BSNs), with multi-agent reinforcement learning (MARL). These methods decompose complex goals into manageable subgoals, creating an intrinsic curriculum that shapes agent learning. We formalize this trend into a framework for Hierarchical Task Environments (HTEs), which are essential for bridging the gap between simple, reactive behaviors and sophisticated, strategic team play. Our framework incorporates the use of Large Language Models (LLMs) as generative world models of tasks, capable of dynamically generating this scaffolding. We argue that HTEs provide a mechanism to guide exploration, generate meaningful learning signals, and train agents to internalize hierarchical structure, enabling the development of more capable and general-purpose agents with greater sample efficiency than purely end-to-end approaches.

Invasion team sports such as soccer produce a high-dimensional, strongly coupled state space as many players continuously interact on a shared field, challenging quantitative tactical analysis. Traditional rule-based analyses are intuitive, while modern predictive machine learning models often perform pattern-matching without explicit agent representations. The problem we address is how to build player-level agent models from data, whose learned values and policies are both tactically interpretable and robust across heterogeneous data sources. Here, we propose Expandable Decision-Making States (EDMS), a semantically enriched state representation that augments raw positions and velocities with relational variables (e.g., scoring of space, pass, and score), combined with an action-masking scheme that gives on-ball and off-ball agents distinct decision sets. Compared to prior work, EDMS maps learned value functions and action policies to human-interpretable tactical concepts (e.g., marking pressure, passing lanes, ball accessibility) instead of raw coordinate features, and aligns agent choices with the rules of play. In the experiments, EDMS with action masking consistently reduced both action-prediction loss and temporal-difference (TD) error compared to the baseline. Qualitative case studies and Q-value visualizations further indicate that EDMS highlights high-risk, high-reward tactical patterns (e.g., fast counterattacks and defensive breakthroughs). We also integrated our approach into an open-source library and demonstrated compatibility with multiple commercial and open datasets, enabling cross-provider evaluation and reproducible experiments.

Achieving coordinated teamwork among legged robots requires both fine-grained locomotion control and long-horizon strategic decision-making. Robot soccer offers a compelling testbed for this challenge, combining dynamic, competitive, and multi-agent interactions. In this work, we present a hierarchical multi-agent reinforcement learning (MARL) framework that enables fully autonomous and decentralized quadruped robot soccer. First, a set of highly dynamic low-level skills is trained for legged locomotion and ball manipulation, such as walking, dribbling, and kicking. On top of these, a high-level strategic planning policy is trained with Multi-Agent Proximal Policy Optimization (MAPPO) via Fictitious Self-Play (FSP). This learning framework allows agents to adapt to diverse opponent strategies and gives rise to sophisticated team behaviors, including coordinated passing, interception, and dynamic role allocation. With an extensive ablation study, the proposed learning method shows significant advantages in the cooperative and competitive multi-agent soccer game. We deploy the learned policies to real quadruped robots relying solely on onboard proprioception and decentralized localization, with the resulting system supporting autonomous robot-robot and robot-human soccer matches on indoor and outdoor soccer courts.

Understanding football tactics is crucial for managers and analysts. Previous research has proposed models based on spatial and kinematic equations, but these are computationally expensive. Also, Reinforcement learning approaches use player positions and velocities but lack interpretability and require large datasets. Rule-based models align with expert knowledge but have not fully considered all players' states. This study explores whether low-dimensional, rule-based models using spatiotemporal data can effectively capture football tactics. Our approach defines interpretable state variables for both the ball-holder and potential pass receivers, based on criteria that explore options like passing. Through discussions with a manager, we identified key variables representing the game state. We then used StatsBomb event data and SkillCorner tracking data from the 2023$/$24 LaLiga season to train an XGBoost model to predict pass success. The analysis revealed that the distance between the player and the ball, as well as the player's space score, were key factors in determining successful passes. Our interpretable low-dimensional modeling facilitates tactical analysis through the use of intuitive variables and provides practical value as a tool to support decision-making in football.

Line-breaking passes (LBPs) are crucial tactical actions in football, allowing teams to penetrate defensive lines and access high-value spaces. In this study, we present an unsupervised, clustering-based framework for detecting and analysing LBPs using synchronised event and tracking data from elite matches. Our approach models opponent team shape through vertical spatial segmentation and identifies passes that disrupt defensive lines within open play. Beyond detection, we introduce several tactical metrics, including the space build-up ratio (SBR) and two chain-based variants, LBPCh$^1$ and LBPCh$^2$, which quantify the effectiveness of LBPs in generating immediate or sustained attacking threats. We evaluate these metrics across teams and players in the 2022 FIFA World Cup, revealing stylistic differences in vertical progression and structural disruption. The proposed methodology is explainable, scalable, and directly applicable to modern performance analysis and scouting workflows.

Soccer is a sport played on a pitch where effective use of space is crucial. Decision-making during transitions, when possession switches between teams, has been increasingly important, but research on space evaluation in these moments has been limited. Recent space evaluation methods such as OBSO (Off-Ball Scoring Opportunity) use scoring probability, so it is not well-suited for assessing areas far from the goal, where transitions typically occur. In this paper, we propose OBPV (Off-Ball Positioning Value) to evaluate space across the pitch, including the starting points of transitions. OBPV extends OBSO by introducing the field value model, which evaluates the entire pitch, and by employing the transition kernel model, which reflects positional specificity through kernel density estimation of pass distributions. Experiments using La Liga 2023/24 season tracking and event data show that OBPV highlights effective space utilization during counter-attacks and reveals team-specific characteristics in how the teams utilize space after positive and negative transitions.

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.