The paper presents a roadmap that identifies four unsolved problems in ML safety: robustness against hazards, monitoring for hazards, alignment of model goals with human intent, and systemic safety.
Out-of-Distribution Dynamics Detection: RL-Relevant Bench- marks and Results
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2roles
background 1polarities
background 1representative citing papers
A hybrid ES-DRL controller uses VAE latent Mahalanobis OOD detection to switch between RL and ES modes for time-varying nonlinear systems.
citing papers explorer
-
Unsolved Problems in ML Safety
The paper presents a roadmap that identifies four unsolved problems in ML safety: robustness against hazards, monitoring for hazards, alignment of model goals with human intent, and systemic safety.
-
Mahalanobis-Guided Latent OOD Detection for Hybrid ES-DRL Control in Time-Varying Systems
A hybrid ES-DRL controller uses VAE latent Mahalanobis OOD detection to switch between RL and ES modes for time-varying nonlinear systems.