{"ID":2836711,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.19885","arxiv_id":"2511.19885","title":"Complex Instruction Following with Diverse Style Policies in Football Games","abstract":"Despite advancements in language-controlled reinforcement learning (LC-RL) for basic domains and straightforward commands (e.g., object manipulation and navigation), effectively extending LC-RL to comprehend and execute high-level or abstract instructions in complex, multi-agent environments, such as football games, remains a significant challenge. To address this gap, we introduce Language-Controlled Diverse Style Policies (LCDSP), a novel LC-RL paradigm specifically designed for complex scenarios. LCDSP comprises two key components: a Diverse Style Training (DST) method and a Style Interpreter (SI). The DST method efficiently trains a single policy capable of exhibiting a wide range of diverse behaviors by modulating agent actions through style parameters (SP). The SI is designed to accurately and rapidly translate high-level language instructions into these corresponding SP. Through extensive experiments in a complex 5v5 football environment, we demonstrate that LCDSP effectively comprehends abstract tactical instructions and accurately executes the desired diverse behavioral styles, showcasing its potential for complex, real-world applications.","short_abstract":"Despite advancements in language-controlled reinforcement learning (LC-RL) for basic domains and straightforward commands (e.g., object manipulation and navigation), effectively extending LC-RL to comprehend and execute high-level or abstract instructions in complex, multi-agent environments, such as football games, re...","url_abs":"https://arxiv.org/abs/2511.19885","url_pdf":"https://arxiv.org/pdf/2511.19885v1","authors":"[\"Chenglu Sun\",\"Shuo Shen\",\"Haonan Hu\",\"Wei Zhou\",\"Chen Chen\"]","published":"2025-11-25T03:45:34Z","proceeding":"cs.MA","tasks":"[\"cs.MA\",\"cs.LG\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}