arXiv research

Paper defines ε-Safe Decision Regions for exponential family distributions and approximates them for unbalanced data.

Enforcing safety is a key aspect of many problems pertaining to sequential decision making under uncertainty, which require the decisions made at every step to be both informative of the optimal decision and also safe. For example, we value both efficacy and comfort in medical therapy, and efficiency and safety in robo…

Safe Bayesian optimization method using information theory.

Proposes a method to accelerate safe sequential learning using offline data.

RYU framework constructs safe regions for optimization problems.

A new screening test for Lasso improves solution speed.

Safe autonomous decisions made with machine learning predictions using Conformal Decision Theory.

Deep neural networks have become widely used, obtaining remarkable results in domains such as computer vision, speech recognition, natural language processing, audio recognition, social network filtering, machine translation, and bio-informatics, where they have produced results comparable to human experts. However, th…

In Interactive Machine Learning (IML), we iteratively make decisions and obtain noisy observations of an unknown function. While IML methods, e.g., Bayesian optimization and active learning, have been successful in applications, on real-world systems they must provably avoid unsafe decisions. To this end, safe IML algo…

Algorithm reduces regret in safe Bayesian optimization with monotonicity constraints.

Safe RL for autonomous vehicles using PCPO with trust regions and parallel learners.

New method avoids failures in physics-constrained systems using active learning.

High dimensional regression benefits from sparsity promoting regularizations. Screening rules leverage the known sparsity of the solution by ignoring some variables in the optimization, hence speeding up solvers. When the procedure is proven not to discard features wrongly the rules are said to be \emph{safe}. In this …

Safe Gaussian Process Bandit Optimization with sub-linear regret bounds.

Safe learning of stochastic dynamics with safety constraints.

In this paper, the problem of safe global maximization (it should not be confused with robust optimization) of expensive noisy black-box functions satisfying the Lipschitz condition is considered. The notion "safe" means that the objective function $f(x)$ during optimization should not violate a "safety" threshold, for…

Algorithm finds safe zones in policy Markov Decision Processes to limit trajectory escape.

In many safety-critical applications such as autonomous driving and surgical robots, it is desirable to obtain prediction uncertainties from object detection modules to help support safe decision-making. Specifically, such modules need to estimate the probability of each predicted object in a given region and the confi…

New method provides scalable safety guarantees for RL agents.

A new algorithm trains experts to safely guide agents in partially observed environments.

Combines Lyapunov functions with controller synthesis for safe control policies.

CoCoRL learns safe constraints from demonstrations with unknown rewards.

ARTEO algorithm optimizes safety-critical systems with uncertainty.

A new RL model ensures safe learning in uncertain environments.

Safe-M$^3$-UCRL learns safe policies for multi-agent systems with global constraints.

In classical reinforcement learning, when exploring an environment, agents accept arbitrary short term loss for long term gain. This is infeasible for safety critical applications, such as robotics, where even a single unsafe action may cause system failure. In this paper, we address the problem of safely exploring fin…

New algorithm learns safe policies in unknown environments.

Safe RL with binary feedback using SABRE algorithm.

Screening rules allow to early discard irrelevant variables from the optimization in Lasso problems, or its derivatives, making solvers faster. In this paper, we propose new versions of the so-called $\textit{safe rules}$ for the Lasso. Based on duality gap considerations, our new rules create safe test regions whose d…

Reinforcement learning is a powerful paradigm for learning optimal policies from experimental data. However, to find optimal policies, most reinforcement learning algorithms explore all possible actions, which may be harmful for real-world systems. As a consequence, learning algorithms are rarely applied on safety-crit…

Safe reinforcement learning framework using optimal transport for robustness.

OSIL learns safe policies from unsafe demonstrations.

Risk-averse model uncertainty framework for safe reinforcement learning.

Safe actions learned in finite trials, without infinite exploration.

Safe RL in linear systems achieves $\sqrt{T}$-regret.

The paper tackles safe exploration in RL by a conservative safety critic.

Simplified screening tests for data points in optimization.

Bayesian optimization sped up with model approximations for safe online system optimization.

Safe learning in uncertain systems with state measurements and optimization.

Investigates safe decision-making in interactive environments.

Fair ML systems can be safe ML systems by considering uncertainty.

In the real world, agents often have to operate in situations with incomplete information, limited sensing capabilities, and inherently stochastic environments, making individual observations incomplete and unreliable. Moreover, in many situations it is preferable to delay a decision rather than run the risk of making …

Framework for safely updating machine learning models.

This work provides safety guarantees for iterative GP predictions.

Previous work has questioned the conditions under which the decision regions of a neural network are connected and further showed the implications of the corresponding theory to the problem of adversarial manipulation of classifiers. It has been proven that for a class of activation functions including leaky ReLU, neur…

We show that for neural network functions that have width less or equal to the input dimension all connected components of decision regions are unbounded. The result holds for continuous and strictly monotonic activation functions as well as for the ReLU activation function. This complements recent results on approxima…

Proposes CPO framework for robust decision-making with explainable uncertainty regions.

New algorithm optimizes reward while ensuring safety in complex decision-making problems.