Risk Sensitive Dead-end Identification in Safety-Critical Offline Reinforcement Learning
In safety-critical decision-making scenarios being able to identify worst-case outcomes, or dead-ends is crucial in order to develop safe and reliable policies in practice. These situations are typically rife with uncertainty due to unknown or stochastic characteristics of the environment as well as limited offline training data. As a result, the value of a decision at any time point should be based on the distribution of its anticipated effects. We propose a framework to identify worst-case decision points, by explicitly estimating distributions of the expected return of a decision. These estimates enable earlier indication of dead-ends in a manner that is tunable based on the risk tolerance of the designed task. We demonstrate the utility of Distributional Dead-end Discovery (DistDeD) in a toy domain as well as when assessing the risk of severely ill patients in the intensive care unit reaching a point where death is unavoidable. We find that DistDeD significantly improves over prior discovery approaches, providing indications of the risk 10 hours earlier on average as well as increasing detection by 20%.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision Makingreinforcement-learningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Action-Conditioned Risk Gating for Safety-Critical Control under Partial Observability
Many safety-critical control problems are modeled as risk-sensitive partially observable Markov decision processes, where the controller must make decisions from incomplete observations while balancing task performance a…
Reinforcement LearningRisk-sensitive Actor-free Policy via Convex Optimization
Traditional reinforcement learning methods optimize agents without considering safety, potentially resulting in unintended consequences. In this paper, we propose an optimal actor-free policy that optimizes a risk-sensit…
reinforcement-learningReinforcement LearningOne Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning
Offline reinforcement learning (RL) is suitable for safety-critical domains where online exploration is too costly or dangerous. In such safety-critical settings, decision-making should take into consideration the risk o…
AllDecision MakingOffline RLReinforcement Learning (RL)+1Dual-Task Learning for Dead Tree Detection and Segmentation with Hybrid Self-Attention U-Nets in Aerial Imagery
Mapping standing dead trees is critical for assessing forest health, monitoring biodiversity, and mitigating wildfire risks, for which aerial imagery has proven useful. However, dense canopy structures, spectral overlaps…
Computational EfficiencySegmentationRegret Bounds for Risk-Sensitive Reinforcement Learning
In safety-critical applications of reinforcement learning such as healthcare and robotics, it is often desirable to optimize risk-sensitive objectives that account for tail outcomes rather than expected reward. We prove …
reinforcement-learningReinforcement LearningReinforcement Learning (RL)