arXiv research

Safe learning of stochastic dynamics with safety constraints.

Safe imitation learning with a safety layer for flexible training.

A new distributed method speeds up sparse model training.

DRSSS method reduces model training costs by eliminating unsafe samples.

We propose a method to optimise the parameters of a policy which will be used to safely perform a given task in a data-efficient manner. We train a Gaussian process model to capture the system dynamics, based on the PILCO framework. Our model has useful analytic properties, which allow closed form computation of error …

Safe reinforcement learning framework using optimal transport for robustness.

Safe sample screening improves RSVM performance without sacrificing accuracy.

Framework trains safe agents avoiding deceptive behavior.

New method provides scalable safety guarantees for RL agents.

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…

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

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

Safe neural networks for input-output specifications.

Screening is an effective technique for speeding up the training process of a sparse learning model by removing the features that are guaranteed to be inactive the process. In this paper, we present a efficient screening technique for sparse support vector machine based on variational inequality. The technique is both …

Risk-averse model uncertainty framework for safe reinforcement learning.

Batch Reinforcement Learning (Batch RL) consists in training a policy using trajectories collected with another policy, called the behavioural policy. Safe policy improvement (SPI) provides guarantees with high probability that the trained policy performs better than the behavioural policy, also called baseline in this…

Safe RL with binary feedback using SABRE algorithm.

Safe Active Learning (SAL) for GPODE models improves model performance without compromising safety.

Sparse classifiers such as the support vector machines (SVM) are efficient in test-phases because the classifier is characterized only by a subset of the samples called support vectors (SVs), and the rest of the samples (non SVs) have no influence on the classification result. However, the advantage of the sparsity has…

Previous work has shown the unreliability of existing algorithms in the batch Reinforcement Learning setting, and proposed the theoretically-grounded Safe Policy Improvement with Baseline Bootstrapping (SPIBB) fix: reproduce the baseline policy in the uncertain state-action pairs, in order to control the variance on th…

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…

We propose a framework for ensuring safe behavior of a reinforcement learning agent when the reward function may be difficult to specify. In order to do this, we rely on the existence of demonstrations from expert policies, and we provide a theoretical framework for the agent to optimize in the space of rewards consist…

Safe linear stochastic bandits ensure safe exploration with optimal regret.

DRSS method identifies unnecessary samples and features in DR covariate shift.

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

Safe screening rule reduces computational costs for Group OWL models.

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

New method uses neural nets to control systems safely with disturbances.

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

Safe screening rule improves Group SLOPE efficiency.

CoCoRL learns safe constraints from demonstrations with unknown rewards.

A bias classifier is introduced to resist adversarial attacks.

SafePILCO is a Python tool for safe reinforcement learning.

Method trains emulators to estimate posterior probabilities safely.

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 …

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 …

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…

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

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…

Bitcoin fails to prove safe haven status during pandemic.

Many online platforms have deployed anti-fraud systems to detect and prevent fraudulent activities. However, there is usually a gap between the time that a user commits a fraudulent action and the time that the user is suspended by the platform. How to detect fraudsters in time is a challenging problem. Most of the exi…

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

Meta-learning priors improves safe Bayesian optimization.

Revel tackles safe exploration in RL with verified symbolic policies.

Safe exploration framework for IML algorithms.

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

Safe reinforcement learning for autonomous vehicles using prediction constraints.

Neural network based approximate computing is a universal architecture promising to gain tremendous energy-efficiency for many error resilient applications. To guarantee the approximation quality, existing works deploy two neural networks (NNs), e.g., an approximator and a predictor. The approximator provides the appro…