Modeling Risk in Reinforcement Learning: A Literature Mapping
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 35 of its 100 references that are in the map. First posted on arXiv 8 Dec 2023.
Builds on
35 of 100 references.
References · 35
- 2016Concrete Problems in AI Safetycited by 1,582
- 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 698
- 2017Safe Reinforcement Learning via Shieldingcited by 427
- 2018Implicit Quantile Networks for Distributional Reinforcement Learningcited by 362
- 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 337
- 2019Reinforcement Learning in Healthcare: A Surveycited by 308
- 2020Responsive Safety in Reinforcement Learning by PID Lagrangian Methodscited by 302
- 2018A Lyapunov-based Approach to Safe Reinforcement Learningcited by 278
- 2019End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Taskscited by 256
- 2021A Practical Guide to Multi-Objective Reinforcement Learning and Planningcited by 240
- 2013Risk-sensitive Reinforcement Learningcited by 129
- 2020Safe Reinforcement Learning in Constrained Markov Decision Processescited by 109
23 more
- 2017Trial without Error: Towards Safe Reinforcement Learning via Human Interventioncited by 102
- 2020Safe Reinforcement Learning via Curriculum Inductioncited by 73
- 2022Safe Reinforcement Learning by Imagining the Near Futurecited by 67
- 2019Being Optimistic to Be Conservative: Quickly Learning a CVaR Policycited by 63
- 2020Reinforcement Learning in Economics and Financecited by 57
- 2021How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Reviewcited by 36
- 2021Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violationscited by 36
- 2022A Review of Uncertainty for Deep Reinforcement Learningcited by 36
- 2020Safe Reinforcement Learning via Projection on a Safe Set: How to Achieve Optimality?cited by 29
- 2020SAMBA: Safe Model-Based & Active Reinforcement Learningcited by 28
- 2020Safe Reinforcement Learning with Natural Language Constraintscited by 22
- 2021Safe Learning and Optimization Techniques: Towards a Survey of the State of the Artcited by 16
- 2021Safe Distributional Reinforcement Learningcited by 10
- 2021Safe Policy Optimization with Local Generalized Linear Function Approximationscited by 10
- 2019Improving Safety in Reinforcement Learning Using Model-Based Architectures and Human Interventioncited by 7
- 2021Model-Based Reinforcement Learning for Approximate Optimal Control with Temporal Logic Specificationscited by 5
- 2021Stability-Constrained Markov Decision Processes Using MPCcited by 4
- 2023Safe and Sample-efficient Reinforcement Learning for Clustered Dynamic Environmentscited by 3
- 2021Automatic Exploration Process Adjustment for Safe Reinforcement Learning with Joint Chance Constraint Satisfactioncited by 2
- 2021Temporal-Logic-Based Intermittent, Optimal, and Safe Continuous-Time Learning for Trajectory Trackingcited by 2
- 2018State-Augmentation Transformations for Risk-Sensitive Reinforcement Learningcited by 1
- 2020Synthesizing Safe Policies under Probabilistic Constraints with Reinforcement Learning and Bayesian Model Checkingcited by 1
- 2021Regular Decision Processes for Grid Worldscited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.