paper-with-me

홈 › Papers

Modeling Risk in Reinforcement Learning: A Literature Mapping

2023-12-08 · Leonardo Villalobos-Arias, Derek Martin, Abhijeet Krishnan, Madeleine Gagné, Colin M. Potts, Arnav Jhala

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.

📄 PDF Abstract BibTeX arXiv:2312.05231

Code (0)

등록된 구현이 없습니다.

Tasks

Managementreinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Reinforcement Learning

Similar Papers 제목 키워드 기반

Mapping AI Benchmark Data to Quantitative Risk Estimates Through Expert Elicitation

2025-03-06 · Malcolm Murray, Henry Papadatos, Otter Quarks, Pierre-François Gimenez 외

The literature and multiple experts point to many potential risks from large language models (LLMs), but there are still very few direct measurements of the actual harms posed. AI risk assessment has so far focused on me…

Average-reward model-free reinforcement learning: a systematic review and literature mapping

2020-10-18 · Vektor Dewanto, George Dunn, Ali Eshragh, Marcus Gallagher 외

Reinforcement learning is important part of artificial intelligence. In this paper, we review model-free reinforcement learning that utilizes the average reward optimality criterion in the infinite horizon setting. Motiv…

Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1

EX-DRL: Hedging Against Heavy Losses with EXtreme Distributional Reinforcement Learning

2024-08-22 · Parvin Malekzadeh, Zissis Poulos, Jacky Chen, Zeyu Wang 외

Recent advancements in Distributional Reinforcement Learning (DRL) for modeling loss distributions have shown promise in developing hedging strategies in derivatives markets. A common approach in DRL involves learning th…

Distributional Reinforcement Learningquantile regression

Dimensional Characterization and Pathway Modeling for Catastrophic AI Risks

2025-08-08 · Ze Shen Chin arxiv

Although discourse around the risks of Artificial Intelligence (AI) has grown, it often lacks a comprehensive, multidimensional framework, and concrete causal pathways mapping hazard to harm. This paper aims to bridge th…

Reinforcement Learning and its Connections with Neuroscience and Psychology

2020-06-25 · Ajay Subramanian, Sharad Chitlangia, Veeky Baths

Reinforcement learning methods have recently been very successful at performing complex sequential tasks like playing Atari games, Go and Poker. These algorithms have outperformed humans in several tasks by learning from…

Atari GamesDecision Makingreinforcement-learningReinforcement Learning+1