Related papers: Distributionally Safe Reinforcement Learning under…

Autonomously controlling quadrotors in large-scale subterranean environments is applicable to many areas such as environmental surveying, mining operations, and search and rescue. Learning-based controllers represent an appealing approach…

Interpretable and explainable machine learning has seen a recent surge of interest. We focus on safety as a key motivation behind the surge and make the relationship between interpretability and safety more quantitative. Toward assessing…

We consider a distributionally robust stochastic optimization problem and formulate it as a stochastic two-level composition optimization problem with the use of the mean--semideviation risk measure. In this setting, we consider a single…

We study the problem of co-designing control barrier functions and linear state feedback controllers for discrete-time linear systems affected by additive disturbances. For disturbances of bounded magnitude, we provide a semi-definite…

The use of neural networks has been very successful in a wide variety of applications. However, it has recently been observed that it is difficult to generalize the performance of neural networks under the condition of distributional shift.…

The main challenge that sets transfer learning apart from traditional supervised learning is the distribution shift, reflected as the shift between the source and target models and that between the marginal covariate distributions. In this…

Several works have addressed the problem of incorporating constraints in the reinforcement learning (RL) framework, however majority of them can only guarantee the satisfaction of soft constraints. In this work, we address the problem of…

In model-based reinforcement learning for safety-critical control systems, it is important to formally certify system properties (e.g., safety, stability) under the learned controller. However, as existing methods typically apply formal…

This paper considers a security constrained dispatch problem involving generation and line contingencies in the presence of the renewable generation. The uncertainty due to renewables is modeled using joint chance-constraint and the…

Safety remains a central challenge in control of dynamical systems, particularly when the boundaries of unsafe sets are complex (e.g., nonconvex, nonsmooth) or unknown. This paper proposes a learning-enabled framework for safety-critical…

We study the problem of meta-learning through the lens of online convex optimization, developing a meta-algorithm bridging the gap between popular gradient-based meta-learning and classical regularization-based multi-task transfer methods.…

For safely applying reinforcement learning algorithms on high-dimensional nonlinear dynamical systems, a simplified system model is used to formulate a safe reinforcement learning framework. Based on the simplified system model, a…

We revisit the fundamental problem of learning with distribution shift, in which a learner is given labeled samples from training distribution $D$, unlabeled samples from test distribution $D'$ and is asked to output a classifier with low…

Operational constraint violations may occur when deep reinforcement learning (DRL) agents interact with real-world active distribution systems to learn their optimal policies during training. This letter presents a universal…

This paper presents a strictly convex chance-constrained stochastic control framework that accounts for uncertainty in control specifications such as reference trajectories and operational constraints. By jointly optimizing control inputs…

Safe reinforcement learning aims to learn a control policy while ensuring that neither the system nor the environment gets damaged during the learning process. For implementing safe reinforcement learning on highly nonlinear and…

Sequential learning methods, such as active learning and Bayesian optimization, aim to select the most informative data for task learning. In many applications, however, data selection is constrained by unknown safety conditions, motivating…

Safe Reinforcement Learning (RL) algorithms are typically evaluated under fixed training conditions. We investigate whether training-time safety guarantees transfer to deployment under distribution shift, using diabetes management as a…

Training machine learning models from data with weak supervision and dataset shifts is still challenging. Designing algorithms when these two situations arise has not been explored much, and existing algorithms cannot always handle the most…

Safety is an essential component for deploying reinforcement learning (RL) algorithms in real-world scenarios, and is critical during the learning process itself. A natural first approach toward safe RL is to manually specify constraints on…