English
Related papers

Related papers: Safety aware model-based reinforcement learning fo…

200 papers

Reinforcement Learning has emerged as a promising framework for developing adaptive and data-driven strategies, enabling market makers to optimize decision-making policies based on interactions with the limit order book environment. This…

Trading and Market Microstructure · Quantitative Finance 2026-02-17 Rafael Zimmer , Oswaldo Luiz do Valle Costa

Reinforcement learning methods require careful design involving a reward function to obtain the desired action policy for a given task. In the absence of hand-crafted reward functions, prior work on the topic has proposed several methods…

Machine Learning · Computer Science 2018-10-16 Daiki Kimura , Subhajit Chaudhury , Ryuki Tachibana , Sakyasingha Dasgupta

Episodic control enables sample efficiency in reinforcement learning by recalling past experiences from an episodic memory. We propose a new model-based episodic memory of trajectories addressing current limitations of episodic control. Our…

Machine Learning · Computer Science 2021-11-09 Hung Le , Thommen Karimpanal George , Majid Abdolshah , Truyen Tran , Svetha Venkatesh

Animals and robots exist in a physical world and must coordinate their bodies to achieve behavioral objectives. With recent developments in deep reinforcement learning, it is now possible for scientists and engineers to obtain sensorimotor…

Robotics · Computer Science 2024-05-21 Yusheng Jiao , Feng Ling , Sina Heydari , Nicolas Heess , Josh Merel , Eva Kanso

In this paper we propose a framework towards achieving two intertwined objectives: (i) equipping reinforcement learning with active exploration and deliberate information gathering, such that it regulates state and parameter uncertainties…

Machine Learning · Computer Science 2024-09-10 Mohammad S. Ramadan , Mahmoud A. Hayajnh , Michael T. Tolley , Kyriakos G. Vamvoudakis

Safe reinforcement learning in nonstationary environments requires safety mechanisms that adapt as environmental conditions change. Standard safe reinforcement learning methods often assume fixed constraints or stable environmental…

Machine Learning · Computer Science 2026-05-20 Timofey Tomashevskiy

Reinforcement learning methods are increasingly used to optimise dialogue policies from experience. Most current techniques are model-free: they directly estimate the utility of various actions, without explicit model of the interaction…

Artificial Intelligence · Computer Science 2013-04-09 Pierre Lison

This paper proposes a Safe Online Control-Informed Learning framework for safety-critical autonomous systems. The framework unifies optimal control, parameter estimation, and safety constraints into an online learning process. It employs an…

Systems and Control · Electrical Eng. & Systems 2025-12-25 Tianyu Zhou , Zihao Liang , Zehui Lu , Shaoshuai Mou

While conventional reinforcement learning focuses on designing agents that can perform one task, meta-learning aims, instead, to solve the problem of designing agents that can generalize to different tasks (e.g., environments, obstacles,…

Machine Learning · Computer Science 2021-09-06 Xiaowu Sun , Wael Fatnassi , Ulices Santa Cruz , Yasser Shoukry

Using control barrier functions (CBFs) as safety filters provides a computationally inexpensive yet effective method for constructing controllers in safety-critical applications. However, using CBFs requires the construction of a valid CBF,…

Systems and Control · Electrical Eng. & Systems 2024-02-15 Bolun Dai , Prashanth Krishnamurthy , Farshad Khorrami

Safety-critical applications require controllers/policies that can guarantee safety with high confidence. The control barrier function is a useful tool to guarantee safety if we have access to the ground-truth system dynamics. In practice,…

Machine Learning · Computer Science 2021-12-30 Athindran Ramesh Kumar , Sulin Liu , Jaime F. Fisac , Ryan P. Adams , Peter J. Ramadge

Soft robotic manipulators offer operational advantage due to their compliant and deformable structures. However, their inherently nonlinear dynamics presents substantial challenges. Traditional analytical methods often depend on simplifying…

Robotics · Computer Science 2024-10-28 Uljad Berdica , Matthew Jackson , Niccolò Enrico Veronese , Jakob Foerster , Perla Maiolino

We propose a novel adaptive reinforcement learning control approach for fault tolerant control of degrading systems that is not preceded by a fault detection and diagnosis step. Therefore, \textit{a priori} knowledge of faults that may…

Systems and Control · Electrical Eng. & Systems 2020-08-12 Ibrahim Ahmed , Marcos Quiñones-Grueiro , Gautam Biswas

The applicability of reinforcement learning (RL) algorithms in real-world domains often requires adherence to safety constraints, a need difficult to address given the asymptotic nature of the classic RL optimization objective. In contrast…

Machine Learning · Computer Science 2021-04-15 Moritz A. Zanger , Karam Daaboul , J. Marius Zöllner

We develop a control algorithm that ensures the safety, in terms of confinement in a set, of a system with unknown, 2nd-order nonlinear dynamics. The algorithm establishes novel connections between data-driven and robust, nonlinear control.…

Systems and Control · Electrical Eng. & Systems 2021-05-17 Christos K. Verginis , Franck Djeumou , Ufuk Topcu

We study in this paper the problem of adaptive trajectory tracking control for a class of nonlinear systems with parametric uncertainties. We propose to use a modular approach, where we first design a robust nonlinear state feedback which…

Systems and Control · Computer Science 2015-09-28 Mouhacine Benosman , Amir-massoud Farahmand , Meng Xia

Learning-based methods have been successful in solving complex control tasks without significant prior knowledge about the system. However, these methods typically do not provide any safety guarantees, which prevents their use in…

Systems and Control · Computer Science 2018-11-08 Torsten Koller , Felix Berkenkamp , Matteo Turchetta , Andreas Krause

Recently, there has been a surge in interest in safe and robust techniques within reinforcement learning (RL). Current notions of risk in RL fail to capture the potential for systemic failures such as abrupt stoppages from system failures…

Systems and Control · Computer Science 2019-10-09 David Mguni

In reinforcement learning, classic on-policy evaluation methods often suffer from high variance and require massive online data to attain the desired accuracy. Previous studies attempt to reduce evaluation variance by searching for or…

Machine Learning · Computer Science 2025-03-21 Claire Chen , Shuze Daniel Liu , Shangtong Zhang

In recent years, advanced model-based and data-driven control methods are unlocking the potential of complex robotics systems, and we can expect this trend to continue at an exponential rate in the near future. However, ensuring safety with…

Robotics · Computer Science 2024-08-29 Gianni Lunardi , Asia La Rocca , Matteo Saveriano , Andrea Del Prete