Safe reinforcement learning deals with mitigating or avoiding unsafe situations by reinforcement learning (RL) agents. Safe RL approaches are based on specific risk representations for particular problems or domains. In order to analyze agent behaviors, compare safe RL approaches, and effectively transfer techniques between application domains, it is necessary to understand the types of risk specific to safe RL problems. We performed a systematic literature mapping with the objective to characterize risk in safe RL. Based on the obtained results, we present definitions, characteristics, and types of risk that hold on multiple application domains. Our literature mapping covers literature from the last 5 years (2017-2022), from a variety of knowledge areas (AI, finance, engineering, medicine) where RL approaches emphasize risk representation and management. Our mapping covers 72 papers filtered systematically from over thousands of papers on the topic. Our proposed notion of risk covers a variety of representations, disciplinary differences, common training exercises, and types of techniques. We encourage researchers to include explicit and detailed accounts of risk in future safe RL research reports, using this mapping as a starting point. With this information, researchers and practitioners could draw stronger conclusions on the effectiveness of techniques on different problems.

翻译：安全强化学习致力于通过强化学习智能体减轻或规避不安全情境。安全强化学习方法基于特定问题或领域的风险表征。为分析智能体行为、比较安全强化学习方法、并有效跨领域迁移技术，需理解安全强化学习问题中风险的特有类型。我们开展了系统性文献图谱研究，旨在表征安全强化学习中的风险。基于研究结果，我们提出了适用于多应用领域的风险定义、特征及类型。本图谱涵盖近五年（2017-2022）来自人工智能、金融、工程、医学等不同知识领域的文献，这些领域中的强化学习方法均强调风险表征与管理。我们从数千篇相关文献中系统筛选出72篇论文构成研究样本。提出的风险概念涵盖了多种表征形式、学科差异、通用训练范式及技术类型。我们鼓励研究者以本图谱为起点，在未来安全强化学习研究报告中明确描述风险的具体细节。凭借此信息，研究人员与实践者能够就不同问题上各种技术的有效性得出更可靠的结论。