arXiv research

Study best arm identification with safety constraints in bandit problems.

Algorithm minimizes regret while adhering to unknown safety constraints.

A new algorithm for identifying the best arm in linear feedback with safety constraints.

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

Safety filter for unknown discrete-time systems with learned models and noise covariance.

Safe reinforcement learning tackles safety constraints with linear approximations.

In order to satisfy safety conditions, an agent may be constrained from acting freely. A safe controller can be designed a priori if an environment is well understood, but not when learning is employed. In particular, reinforcement learned (RL) controllers require exploration, which can be hazardous in safety critical …

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

Study examines sample complexity for RL with safety constraints.

Investigates safe decision-making in interactive environments.

A new RL model ensures safe learning in uncertain environments.

Logarithmic regret strategies for safe multi-armed bandits with safety risk constraints.

Safe linear bandits over unknown polytopes avoid safety violations and suboptimal actions.

We propose Trusted Neural Network (TNN) models, which are deep neural network models that satisfy safety constraints critical to the application domain. We investigate different mechanisms for incorporating rule-based knowledge in the form of first-order logic constraints into a TNN model, where rules that encode safet…

Safe learning of stochastic dynamics with safety constraints.

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…

Paper proposes Vertex Networks for reinforcement learning of control systems with safety guarantees.

Proposes a recursive MPC scheme with probabilistic safety guarantees for uncertain dynamic systems.

Meta-learning priors improves safe Bayesian optimization.

ARTEO algorithm optimizes safety-critical systems with uncertainty.

The paper tackles MAP inference over non-convex constraints in safety-critical settings.

New RL approach tackles constrained Markov decision processes.

This paper presents a distributionally robust Q-Learning algorithm (DrQ) which leverages Wasserstein ambiguity sets to provide idealistic probabilistic out-of-sample safety guarantees during online learning. First, we follow past work by separating the constraint functions from the principal objective to create a hiera…

Iterative method learns unknown constraints for MPC control.

The paper tackles safe reinforcement learning with convex regularization.

New method provides scalable safety guarantees for RL agents.

A new error bound improves safety in Bayesian optimization.

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…

Safe reinforcement learning with logical constraints for optimal policy synthesis.

In many real-world reinforcement learning (RL) problems, besides optimizing the main objective function, an agent must concurrently avoid violating a number of constraints. In particular, besides optimizing performance it is crucial to guarantee the safety of an agent during training as well as deployment (e.g. a robot…

This work establishes safe reinforcement learning for LQR with nonlinear baselines.

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

Recent advances in contextual bandit optimization and reinforcement learning have garnered interest in applying these methods to real-world sequential decision making problems. Real-world applications frequently have constraints with respect to a currently deployed policy. Many of the existing constraint-aware algorith…

New algorithm achieves sublinear regret in CMDPs without error cancellations.

Failures are challenging for learning to control physical systems since they risk damage, time-consuming resets, and often provide little gradient information. Adding safety constraints to exploration typically requires a lot of prior knowledge and domain expertise. We present a safety measure which implicitly captures…

Safe Bayesian optimization tackles safety constraints in control engineering.

The design and performance analysis of bandit algorithms in the presence of stage-wise safety or reliability constraints has recently garnered significant interest. In this work, we consider the linear stochastic bandit problem under additional \textit{linear safety constraints} that need to be satisfied at each round.…

Safe active learning for multi-output Gaussian processes reduces data acquisition costs and ensures safety.

New algorithm for reinforcement learning in uncertain environments with unknown thresholds.

A new ML method teaches constraints directly to models.

Recent successes in reinforcement learning have lead to the development of complex controllers for real-world robots. As these robots are deployed in safety-critical applications and interact with humans, it becomes critical to ensure safety in order to avoid causing harm. A first step in this direction is to test the …

Algorithm ensures safe optimization under unknown constraints.

CoCoRL learns safe constraints from demonstrations with unknown rewards.

We study the constrained linear quadratic regulator with unknown dynamics, addressing the tension between safety and exploration in data-driven control techniques. We present a framework which allows for system identification through persistent excitation, while maintaining safety by guaranteeing the satisfaction of st…

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

Safety is a desirable property that can immensely increase the applicability of learning algorithms in real-world decision-making problems. It is much easier for a company to deploy an algorithm that is safe, i.e., guaranteed to perform at least as well as a baseline. In this paper, we study the issue of safety in cont…

DePAint solves MARL for agents with local constraints, privacy, and no central controller.

SDF-Bayes finds safe drug combinations safely, balancing optimism and caution.