arXiv research

Safe learning of stochastic dynamics with safety constraints.

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…

Safe Bayesian optimization tackles safety constraints in control engineering.

Safe learning in uncertain systems with state measurements and optimization.

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

Meta-learning priors improves safe Bayesian optimization.

This paper proposes a method to safely adjust exploration in RL to satisfy constraints.

Combines Lyapunov functions with controller synthesis for safe control policies.

SafePILCO is a Python tool for safe reinforcement learning.

Safe reinforcement learning framework using optimal transport for robustness.

Adapts safe policies for exploration in high-risk settings.

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…

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 …

Meta-active learning optimizes control of safety-critical systems by efficiently learning dynamics and configurations.

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

Using reinforcement learning to learn control policies is a challenge when the task is complex with potentially long horizons. Ensuring adequate but safe exploration is also crucial for controlling physical systems. In this paper, we use temporal logic to facilitate specification and learning of complex tasks. We combi…

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…

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 offline RL for chemical reactors using input convex neural networks.

This paper addresses error bounds and posterior variance for Gaussian process regression.

Reinforcement Learning (RL) methods have been proven successful in solving manipulation tasks autonomously. However, RL is still not widely adopted on real robotic systems because working with real hardware entails additional challenges, especially when using rigid position-controlled manipulators. These challenges inc…

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

Motivated by vision-based control of autonomous vehicles, we consider the problem of controlling a known linear dynamical system for which partial state information, such as vehicle position, is extracted from complex and nonlinear data, such as a camera image. Our approach is to use a learned perception map that predi…

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

This work improves motion planning for quadcopters by learning and reasoning about controller performance.

Quantum model improves safety in machine learning.

Risk control improves EENNs to make faster predictions without sacrificing accuracy.

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…

Tail-Safe hedging uses reinforcement learning with a safety layer to manage financial risks.

Data-driven models are subject to model errors due to limited and noisy training data. Key to the application of such models in safety-critical domains is the quantification of their model error. Gaussian processes provide such a measure and uniform error bounds have been derived, which allow safe control based on thes…

Risk-averse model uncertainty framework for safe reinforcement learning.

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

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…

Safe RL with binary feedback using SABRE algorithm.

We tune one of the most common heating, ventilation, and air conditioning (HVAC) control loops, namely the temperature control of a room. For economical and environmental reasons, it is of prime importance to optimize the performance of this system. Buildings account from 20 to 40% of a country energy consumption, and …

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…

Develops a learning model predictive controller for competitive racing.

Framework trains safe agents avoiding deceptive behavior.

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…

The paper provides a non-asymptotic error bound for linear system identification under nonlinear policies.

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

Gaussian Processes (GPs) are widely employed in control and learning because of their principled treatment of uncertainty. However, tracking uncertainty for iterative, multi-step predictions in general leads to an analytically intractable problem. While approximation methods exist, they do not come with guarantees, mak…

New bounds for kernel regression under non-Gaussian noise.

Control Barrier Functions (CBF) have been recently utilized in the design of provably safe feedback control laws for nonlinear systems. These feedback control methods typically compute the next control input by solving an online Quadratic Program (QP). Solving QP in real-time can be a computationally expensive process …

Safe RL-based vibration control using LQR guidance.

We study the safe reinforcement learning problem with nonlinear function approximation, where policy optimization is formulated as a constrained optimization problem with both the objective and the constraint being nonconvex functions. For such a problem, we construct a sequence of surrogate convex constrained optimiza…

Reinforcement learning algorithms rely on exploration to discover new behaviors, which is typically achieved by following a stochastic policy. In continuous control tasks, policies with a Gaussian distribution have been widely adopted. Gaussian exploration however does not result in smooth trajectories that generally c…

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