Related papers: Predictive Safety Shield for Dyna-Q Reinforcement …
Meta-reinforcement learning (Meta-RL) facilitates rapid adaptation to unseen tasks but faces challenges in long-horizon environments. Skill-based approaches tackle this by decomposing state-action sequences into reusable skills and…
Purpose: This study aims to address the challenges of controlling unstable and nonlinear systems by proposing an adaptive PID controller based on predictive reinforcement learning (PRL-PID), where the PRL-PID combines the advantages of both…
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 is a model-free optimal control method that optimizes a control policy through direct interaction with the environment. For reaching tasks that end in regulation, popular discrete-action methods are not well suited…
There have been attempts in reinforcement learning to exploit a priori knowledge about the structure of the system. This paper proposes a hybrid reinforcement learning controller which dynamically interpolates a model-based linear…
Several works have addressed the problem of incorporating constraints in the reinforcement learning (RL) framework, however majority of them can only guarantee the satisfaction of soft constraints. In this work, we address the problem of…
Deep Neural Network-based systems are now the state-of-the-art in many robotics tasks, but their application in safety-critical domains remains dangerous without formal guarantees on network robustness. Small perturbations to sensor inputs…
Reinforcement Learning (RL) algorithms show amazing performance in recent years, but placing RL in real-world applications such as self-driven vehicles may suffer safety problems. A self-driven vehicle moving to a target position following…
Due to the nature of risk management in learning applicable policies, risk-sensitive reinforcement learning (RSRL) has been realized as an important direction. RSRL is usually achieved by learning risk-sensitive objectives characterized by…
Reinforcement learning (RL) is ubiquitous in the development of modern AI systems. However, state-of-the-art RL agents require extensive, and potentially unsafe, interactions with their environments to learn effectively. These limitations…
Diffusion models have emerged as a powerful approach for multimodal motion planning in autonomous driving. However, their practical deployment is typically hindered by the inherent difficulty in enforcing vehicle dynamics and a critical…
This paper introduces the reinforcement learning backup shield (RLBUS), an algorithm that guarantees safe exploration in reinforcement learning (RL) by incorporating backup control barrier functions (BCBFs). RLBUS constructs an implicit…
Deep Reinforcement Learning (RL) has shown promise in addressing complex robotic challenges. In real-world applications, RL is often accompanied by failsafe controllers as a last resort to avoid catastrophic events. While necessary for…
Although recent model-free reinforcement learning algorithms have been shown to be capable of mastering complicated decision-making tasks, the sample complexity of these methods has remained a hurdle to utilizing them in many real-world…
Many sequential decision-making problems that are currently automated, such as those in manufacturing or recommender systems, operate in an environment where there is either little uncertainty, or zero risk of catastrophe. As companies and…
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…
Safety is a critical component of autonomous systems and remains a challenge for learning-based policies to be utilized in the real world. In particular, policies learned using reinforcement learning often fail to generalize to novel…
Safety guarantee is essential in many engineering implementations. Reinforcement learning provides a useful way to strengthen safety. However, reinforcement learning algorithms cannot completely guarantee safety over realistic operations.…
Safe reinforcement learning (RL) that solves constraint-satisfactory policies provides a promising way to the broader safety-critical applications of RL in real-world problems such as robotics. Among all safe RL approaches, model-based…
Q-learning and SARSA are foundational reinforcement learning algorithms whose practical success depends critically on step-size calibration. Step-sizes that are too large can cause numerical instability, while step-sizes that are too small…