PulseAugur
EN
LIVE 21:33:51

AI optimizes football tactics and creates human-like game agents

By PulseAugur Editorial · [3 sources] ·

Researchers have developed a graph reinforcement learning approach to optimize football corner kick tactics, aiming to discover novel player configurations beyond historical patterns. This method, evaluated on thousands of Premier League corners, significantly outperforms traditional optimization techniques. Separately, a sample-efficient reinforcement learning method has been created to train human-like AI agents for video games, demonstrated by a goalkeeper in EA SPORTS FC 25 that surpasses the game's built-in AI. AI

IMPACT These advancements demonstrate AI's growing capability in strategic optimization for sports and realistic agent behavior in video games.

RANK_REASON The cluster contains two academic papers detailing novel AI approaches for sports and gaming.

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

COVERAGE [3]

  1. arXiv cs.LG TIER_1 English(EN) · Sean Groom, Michael Groom, Francisco Belo, Axl Rice, Liam Anderson, Victor-Alexandru Darvariu, Shuo Wang ·

    Maximising the Set-Piece Return: Optimising Football Corner Tactics with Graph Reinforcement Learning

    arXiv:2606.06353v1 Announce Type: new Abstract: Machine learning is increasingly employed for the evaluation of football tactics. However, existing approaches focus on characterising historical actions or analyst-specified counterfactual scenarios. In this work, we seek to go bey…

  2. arXiv cs.LG TIER_1 English(EN) · Shuo Wang ·

    Maximising the Set-Piece Return: Optimising Football Corner Tactics with Graph Reinforcement Learning

    Machine learning is increasingly employed for the evaluation of football tactics. However, existing approaches focus on characterising historical actions or analyst-specified counterfactual scenarios. In this work, we seek to go beyond the imitation of historically observed patte…

  3. arXiv cs.AI TIER_1 English(EN) · Alessandro Sestini, Joakim Bergdahl, Jean-Philippe Barrette-LaPierre, Florian Fuchs, Brady Chen, Fabio Zinno, Michael Jones, Linus Gissl\'en ·

    Human-Like Goalkeeping in a Realistic Football Simulation: a Sample-Efficient Reinforcement Learning Approach

    arXiv:2510.23216v4 Announce Type: replace Abstract: 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…

RELATED ENTITIES

RELATED TOPICS