Related papers: Barrier-Certified Adaptive Reinforcement Learning …
For robotic vehicles to navigate robustly and safely in unseen environments, it is crucial to decide the most suitable navigation policy. However, most existing deep reinforcement learning based navigation policies are trained with a…
Ensuring safe exploration in high-dimensional systems with unknown dynamics remains a significant challenge. Existing safe reinforcement learning methods often provide safety guarantees only in expectation, which can still lead to safety…
We investigate robust model-free reinforcement learning algorithms designed for environments that may be dynamic or even adversarial. Traditional state-based policies often struggle to accommodate the challenges imposed by the presence of…
In this work, we consider the problem of designing a safety filter for a nonlinear uncertain control system. Our goal is to augment an arbitrary controller with a safety filter such that the overall closed-loop system is guaranteed to stay…
Identifying uncertainty and taking mitigating actions is crucial for safe and trustworthy reinforcement learning agents, especially when deployed in high-risk environments. In this paper, risk sensitivity is promoted in a model-based…
Reinforcement learning provides an appealing framework for robotic control due to its ability to learn expressive policies purely through real-world interaction. However, this requires addressing real-world constraints and avoiding…
Reinforcement Learning (RL) has been shown to be effective in many scenarios. However, it typically requires the exploration of a sufficiently large number of state-action pairs, some of which may be unsafe. Consequently, its application to…
This article presents novel methods for synthesizing distributionally robust stabilizing neural controllers and certificates for control systems under model uncertainty. A key challenge in designing controllers with stability guarantees for…
Reinforcement learning is a promising approach to synthesizing policies for challenging robotics tasks. A key problem is how to ensure safety of the learned policy---e.g., that a walking robot does not fall over or that an autonomous car…
We consider the challenge of finding a deterministic policy for a Markov decision process that uniformly (in all states) maximizes one reward subject to a probabilistic constraint over a different reward. Existing solutions do not fully…
The increasing use of machine learning in safety-critical domains amplifies the risk of adversarial threats, especially data poisoning attacks that corrupt training data to degrade performance or induce unsafe behavior. Most existing…
Scenarios requiring humans to choose from multiple seemingly optimal actions are commonplace, however standard imitation learning often fails to capture this behavior. Instead, an over-reliance on replicating expert actions induces…
To provide safety guarantees for learning-based control systems, recent work has developed formal verification methods to apply after training ends. However, if the trained policy does not meet the specifications, or there is conservatism…
Autonomous vehicles with a self-evolving ability are expected to cope with unknown scenarios in the real-world environment. Take advantage of trial and error mechanism, reinforcement learning is able to self evolve by learning the optimal…
Reinforcement learning has been successfully used to solve difficult tasks in complex unknown environments. However, these methods typically do not provide any safety guarantees during the learning process. This is particularly problematic,…
Reinforcement learning (RL) agents with pre-specified reward functions cannot provide guaranteed safety across variety of circumstances that an uncertain system might encounter. To guarantee performance while assuring satisfaction of safety…
This paper introduces a learning-based framework for robot adaptive manipulating the object with a revolute joint in unstructured environments. We concentrate our discussion on various cabinet door opening tasks. To improve the performance…
This paper addresses the problem of guiding a quadrotor through a predefined sequence of waypoints in cluttered environments, aiming to minimize the flight time while avoiding collisions. Previous approaches either suffer from prolonged…
We propose an adaptive Model Predictive Safety Certification (MPSC) scheme for learning-based control of linear systems with bounded disturbances and uncertain parameters where the true parameters are contained within an a priori known set…
The subject of this paper is reinforcement learning. Policies are considered here that produce actions based on states and random elements autocorrelated in subsequent time instants. Consequently, an agent learns from experiments that are…