Learning to control an uncertain system is a problem with a plethora ofapplications in various engineering elds. In the majority of practical scenarios,one wishes that the learning process terminates quickly and does not violatesafety limits on key variables. It is particularly appealing to learn the controlpolicy directly from experiments, since this eliminates the need to rst derivean accurate physical model of the system. The main challenge when using suchan approach is to ensure safety constraints during the learning process.This thesis investigates an approach to safe learning that relies on a partlyknown state-space model of the system and regards the unknown dynamics asan additive bounded disturbance. Based on an initial conservative...
Safety is an important aim in designing safe-critical systems. To design such systems, many policy i...
The problem of safely learning and controlling a dynamical system - i.e., of stabilizing an original...
We study the problem of safe learning and exploration in sequential control problems. The goal is to...
Learning to control an uncertain system is a problem with a plethora ofapplications in various engin...
Abstract — Reinforcement learning for robotic applications faces the challenge of constraint satisfa...
Reinforcement Learning (RL) algorithms have found limited success beyond simulated applications, and...
The ability to learn and execute optimal control policies safely is critical to the realization of c...
This thesis presents a safety-aware learning framework that employs an adaptivemodel learning method...
The increasing impact of data-driven technologies across various industries has sparked renewed inte...
Forsterkende læring holder løfte om å gjøre det mulig for autonome systemer å tilegne seg nye ferd...
Real-world autonomous systems are often controlled using conventional model-based control methods. B...
Modern nonlinear control theory seeks to endow systems with properties of stability and safety, and ...
Reinforcement learning is an increasingly popular framework that enables robots to learn to perform ...
Safe Curriculum Learning aims at improving safety and efficiency aspects of Reinforcement Learning (...
This paper proposes an on-policy reinforcement learning (RL) control algorithm that solves the optim...
Safety is an important aim in designing safe-critical systems. To design such systems, many policy i...
The problem of safely learning and controlling a dynamical system - i.e., of stabilizing an original...
We study the problem of safe learning and exploration in sequential control problems. The goal is to...
Learning to control an uncertain system is a problem with a plethora ofapplications in various engin...
Abstract — Reinforcement learning for robotic applications faces the challenge of constraint satisfa...
Reinforcement Learning (RL) algorithms have found limited success beyond simulated applications, and...
The ability to learn and execute optimal control policies safely is critical to the realization of c...
This thesis presents a safety-aware learning framework that employs an adaptivemodel learning method...
The increasing impact of data-driven technologies across various industries has sparked renewed inte...
Forsterkende læring holder løfte om å gjøre det mulig for autonome systemer å tilegne seg nye ferd...
Real-world autonomous systems are often controlled using conventional model-based control methods. B...
Modern nonlinear control theory seeks to endow systems with properties of stability and safety, and ...
Reinforcement learning is an increasingly popular framework that enables robots to learn to perform ...
Safe Curriculum Learning aims at improving safety and efficiency aspects of Reinforcement Learning (...
This paper proposes an on-policy reinforcement learning (RL) control algorithm that solves the optim...
Safety is an important aim in designing safe-critical systems. To design such systems, many policy i...
The problem of safely learning and controlling a dynamical system - i.e., of stabilizing an original...
We study the problem of safe learning and exploration in sequential control problems. The goal is to...