让游戏智能体读懂抽象战术指令并执行多样风格动作
Complex Instruction Following with Diverse Style Policies in Football Games
- 用风格参数统一控制多种行为，训练单一策略应对复杂场景
- 在5v5足球环境中成功理解并执行抽象战术指令
- 适合需要多风格智能体的复杂协作任务研究
尽管语言控制强化学习（LC-RL）在基础任务和简单指令（如物体操作与导航）中取得进展，但将其扩展至复杂多智能体环境（如足球比赛）中理解和执行高层或抽象指令仍面临重大挑战。为此，我们提出语言控制多样风格策略（LCDSP），一种专为复杂场景设计的新型LC-RL范式。LCDSP包含两个核心组件：多样风格训练（DST）方法与风格解释器（SI）。DST通过调节风格参数（SP）高效训练单一策略，使其能呈现丰富多样的行为模式；SI则可快速准确地将高层语言指令转化为对应的风格参数。在复杂的5v5足球环境中进行大量实验表明，LCDSP能有效理解抽象战术指令，并精确执行期望的多样化行为风格，展现出在复杂真实应用中的潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。