Modeling Risk in Reinforcement Learning: A Literature Mapping
This work provides a foundational framework for researchers and practitioners to better analyze, compare, and transfer safe RL techniques by clarifying risk representations, addressing a gap in the field.
The authors conducted a systematic literature mapping to characterize risk in safe reinforcement learning, analyzing 72 papers from 2017-2022 across domains like AI, finance, engineering, and medicine, and proposed definitions and types of risk that apply across multiple application domains.
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.