从像素到数字代理：关于强化学习环境分类和技术趋势的实证研究
From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments
AI总结：
本文通过大规模数据分析，研究强化学习环境从物理模拟到通用代理的演变，揭示领域分为语义优先和领域特定泛化两大生态，并提出设计下一代具身语义模拟器的路线图。
摘要：
强化学习（RL）的显著进展本质上与用于训练和评估人工代理的环境密切相关。本研究通过处理大量学术文献并严格提炼超过2000篇核心出版物，提出了一种定量方法，映射从孤立物理模拟到通用、语言驱动的基础代理的转变。通过实施一种新的多维分类法，我们系统分析了针对不同应用领域和必要认知能力的基准测试。我们的自动语义和统计分析揭示了一个深刻的数据验证范式转变：领域分裂为由大型语言模型（LLMs）主导的“语义优先”生态系统和“领域特定泛化”生态系统。此外，我们刻画了这些不同领域的“认知指纹”，以揭示跨任务协同、多领域干扰和零样本泛化背后的机制。最终，本研究为设计下一代具身语义模拟器提供了严谨的定量路线图，弥合了连续物理控制与高级逻辑推理之间的差距。
英文摘要：
The remarkable progress of reinforcement learning (RL) is intrinsically tied to the environments used to train and evaluate artificial agents. Moving beyond traditional qualitative reviews, this work presents a large-scale, data-driven empirical investigation into the evolution of RL environments. By programmatically processing a massive corpus of academic literature and rigorously distilling over 2,000 core publications, we propose a quantitative methodology to map the transition from isolated physical simulations to generalist, language-driven foundation agents. Implementing a novel, multi-dimensional taxonomy, we systematically analyze benchmarks against diverse application domains and requisite cognitive capabilities. Our automated semantic and statistical analysis reveals a profound, data-verified paradigm shift: the bifurcation of the field into a "Semantic Prior" ecosystem dominated by Large Language Models (LLMs) and a "Domain-Specific Generalization" ecosystem. Furthermore, we characterize the "cognitive fingerprints" of these distinct domains to uncover the underlying mechanisms of cross-task synergy, multi-domain interference, and zero-shot generalization. Ultimately, this study offers a rigorous, quantitative roadmap for designing the next generation of Embodied Semantic Simulators, bridging the gap between continuous physical control and high-level logical reasoning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
