arXiv research

OSIL learns safe policies from unsafe demonstrations.

Framework trains safe agents avoiding deceptive behavior.

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…

A new method for CMDP solving without compromising safety constraints.

The paper assesses text classification robustness through maximal safe radius computation.

Algorithm reduces regret in safe Bayesian optimization with monotonicity constraints.

Algorithm safely learns from sub-optimal baseline policies while satisfying constraints.

Early stopping helps prevent overfitting to noisy labels in neural networks.

A novel approach for safe offline RL using latent safety constraints.

Improves policies with high certainty, even in small samples.

Aims to create safe reinforcement learning policies by considering individual harm.

Safe reinforcement learning with logical constraints for optimal policy synthesis.

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…

Weakly supervised data are widespread and have attracted much attention. However, since label quality is often difficult to guarantee, sometimes the use of weakly supervised data will lead to unsatisfactory performance, i.e., performance degradation or poor performance gains. Moreover, it is usually not feasible to man…

CoCoRL learns safe constraints from demonstrations with unknown rewards.

New method tackles safe reinforcement learning from offline data.

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

Study on neural networks to identify redundancy issues in safe machine learning.

Safe linear stochastic bandits ensure safe exploration with optimal regret.

Framework uses human feedback to safely set OOD detection thresholds, reducing false positives.

An investor trades a safe and several risky assets with linear price impact to maximize expected utility from terminal wealth. In the limit for small impact costs, we explicitly determine the optimal policy and welfare, in a general Markovian setting allowing for stochastic market, cost, and preference parameters. Thes…

Safe learning of stochastic dynamics with safety constraints.

We show that when a third party, the adversary, steps into the two-party setting (agent and operator) of safely interruptible reinforcement learning, a trade-off has to be made between the probability of following the optimal policy in the limit, and the probability of escaping a dangerous situation created by the adve…

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

Meta-learning priors improves safe Bayesian optimization.

Bandit algorithms have various application in safety-critical systems, where it is important to respect the system constraints that rely on the bandit's unknown parameters at every round. In this paper, we formulate a linear stochastic multi-armed bandit problem with safety constraints that depend (linearly) on an unkn…

We study the problem of safe learning and exploration in sequential control problems. The goal is to safely collect data samples from operating in an environment, in order to learn to achieve a challenging control goal (e.g., an agile maneuver close to a boundary). A central challenge in this setting is how to quantify…

FISAR uses neural networks to optimize safe reinforcement learning with forward-invariant constraints.

Deployment of deep neural networks (DNNs) in safety- or security-critical systems requires provable guarantees on their correct behaviour. A common requirement is robustness to adversarial perturbations in a neighbourhood around an input. In this paper we focus on the $L_0$ norm and aim to compute, for a trained DNN an…

We study safe screening for metric learning. Distance metric learning can optimize a metric over a set of triplets, each one of which is defined by a pair of same class instances and an instance in a different class. However, the number of possible triplets is quite huge even for a small dataset. Our safe triplet scree…

Safe RL with binary feedback using SABRE algorithm.

In high dimensional regression settings, sparsity enforcing penalties have proved useful to regularize the data-fitting term. A recently introduced technique called screening rules propose to ignore some variables in the optimization leveraging the expected sparsity of the solutions and consequently leading to faster s…

A model used for velocity control during car following was proposed based on deep reinforcement learning (RL). To fulfil the multi-objectives of car following, a reward function reflecting driving safety, efficiency, and comfort was constructed. With the reward function, the RL agent learns to control vehicle speed in …

Paper solves investment strategy optimization with deep learning.

Safe imitation learning with a safety layer for flexible training.

CRPO solves challenging SRL problems with convergence guarantee.

Framework for safely updating machine learning models.

Safe exploration framework for IML algorithms.

Investigates fund separations and stability for long-term optimal investments.

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

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

A new screening test for Lasso improves solution speed.

Proposes Constrained Q-learning for reinforcement learning with constraints.

A new error bound improves safety in Bayesian optimization.

In this work we seek for an approach to integrate safety in the learning process that relies on a partly known state-space model of the system and regards the unknown dynamics as an additive bounded disturbance. We introduce a framework for safely learning a control strategy for a given system with an additive disturba…

Quantum model improves safety in machine learning.

In kernel methods, the median heuristic has been widely used as a way of setting the bandwidth of RBF kernels. While its empirical performances make it a safe choice under many circumstances, there is little theoretical understanding of why this is the case. Our aim in this paper is to advance our understanding of the …

Adapts safe policies for exploration in high-risk settings.