arXiv research

CoCoRL learns safe constraints from demonstrations with unknown rewards.

SafePILCO is a Python tool for safe reinforcement learning.

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

Safe learning of stochastic dynamics with safety constraints.

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

OSIL learns safe policies from unsafe demonstrations.

Meta-learning priors improves safe Bayesian optimization.

Revel tackles safe exploration in RL with verified symbolic policies.

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…

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…

ASE safely explores unknown MDPs with unknown dynamics, improving sample efficiency.

We introduce the safe linear stochastic bandit framework---a generalization of linear stochastic bandits---where, in each stage, the learner is required to select an arm with an expected reward that is no less than a predetermined (safe) threshold with high probability. We assume that the learner initially has knowledg…

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…

SAMBA improves safe reinforcement learning with active exploration metrics.

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…

Safe RL with binary feedback using SABRE algorithm.

Safe reinforcement learning framework using optimal transport for robustness.

Quantum model improves safety in machine learning.

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

Safe imitation learning with a safety layer for flexible training.

Safe actions learned in finite trials, without infinite exploration.

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

Risk-averse model uncertainty framework for safe reinforcement learning.

New method provides scalable safety guarantees for RL agents.

Safe reinforcement learning with logical constraints for optimal policy synthesis.

There have been numerous advances in reinforcement learning, but the typically unconstrained exploration of the learning process prevents the adoption of these methods in many safety critical applications. Recent work in safe reinforcement learning uses idealized models to achieve their guarantees, but these models do …

In reinforcement learning, agents learn by performing actions and observing their outcomes. Sometimes, it is desirable for a human operator to \textit{interrupt} an agent in order to prevent dangerous situations from happening. Yet, as part of their learning process, agents may link these interruptions, that impact the…

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

The problem of learning a sparse model is conceptually interpreted as the process of identifying active features/samples and then optimizing the model over them. Recently introduced safe screening allows us to identify a part of non-active features/samples. So far, safe screening has been individually studied either fo…

This paper addresses the question of how a previously available control policy $π_s$ can be used as a supervisor to more quickly and safely train a new learned control policy $π_L$ for a robot. A weighted average of the supervisor and learned policies is used during trials, with a heavier weight initially on the superv…

Safe learning in uncertain systems with state measurements and optimization.

New method tackles safe reinforcement learning from offline data.

We consider the problem of learning a sparse rule model, a prediction model in the form of a sparse linear combination of rules, where a rule is an indicator function defined over a hyper-rectangle in the input space. Since the number of all possible such rules is extremely large, it has been computationally intractabl…

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

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…

Exploration-exploitation of functions, that is learning and optimizing a mapping between inputs and expected outputs, is ubiquitous to many real world situations. These situations sometimes require us to avoid certain outcomes at all cost, for example because they are poisonous, harmful, or otherwise dangerous. We test…

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…

Safe Bayesian optimization method using information theory.

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…

Optimal and safe semi-supervised learning estimator for high-dimensional data.

Safe Bayesian optimization tackles safety constraints in control engineering.

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

Safe exploration method for RL under disturbance ensures safety with probabilistic guarantees.

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

The paper accelerates regression algorithms by identifying saturated coordinates.

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…

Machine learning can provide efficient solutions to the complex problems encountered in autonomous driving, but ensuring their safety remains a challenge. A number of authors have attempted to address this issue, but there are few publicly-available tools to adequately explore the trade-offs between functionality, scal…

Safe-EF improves federated learning for non-smooth, constrained optimization.