English
Related papers

Related papers: Safe Option-Critic: Learning Safety in the Option-…

200 papers

We show that when a third party, the adversary, steps into the two-party setting (agent and operator) of safely interruptible reinforcement learning, a trade-off has to be made between the probability of following the optimal policy in the…

Machine Learning · Computer Science 2018-05-30 Henrik Aslund , El Mahdi El Mhamdi , Rachid Guerraoui , Alexandre Maurer

This paper targets the efficient construction of a safety shield for decision making in scenarios that incorporate uncertainty. Markov decision processes (MDPs) are prominent models to capture such planning problems. Reinforcement learning…

Artificial Intelligence · Computer Science 2019-11-26 Nils Jansen , Bettina Könighofer , Sebastian Junges , Alexandru C. Serban , Roderick Bloem

We address the problem of deploying a reinforcement learning (RL) agent on a physical system such as a datacenter cooling unit or robot, where critical constraints must never be violated. We show how to exploit the typically smooth dynamics…

Artificial Intelligence · Computer Science 2018-01-29 Gal Dalal , Krishnamurthy Dvijotham , Matej Vecerik , Todd Hester , Cosmin Paduraru , Yuval Tassa

When a robot autonomously performs a complex task, it frequently must balance competing objectives while maintaining safety. This becomes more difficult in uncertain environments with stochastic outcomes. Enhancing transparency in the…

Robotics · Computer Science 2024-06-19 Peter Amorese , Shohei Wakayama , Nisar Ahmed , Morteza Lahijanian

Ensuring the safety of Reinforcement Learning (RL) is crucial for its deployment in real-world applications. Nevertheless, managing the trade-off between reward and safety during exploration presents a significant challenge. Improving…

Machine Learning · Computer Science 2025-03-04 Shangding Gu , Bilgehan Sel , Yuhao Ding , Lu Wang , Qingwei Lin , Ming Jin , Alois Knoll

We introduce the safe linear stochastic bandit framework---a generalization of linear stochastic bandits---where, in each stage, the learner is required to select an arm with an expected reward that is no less than a predetermined (safe)…

Machine Learning · Statistics 2019-11-22 Kia Khezeli , Eilyan Bitar

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,…

Systems and Control · Electrical Eng. & Systems 2019-07-02 Torsten Koller , Felix Berkenkamp , Matteo Turchetta , Joschka Boedecker , Andreas Krause

In safe reinforcement learning, agent needs to balance between exploration actions and safety constraints. Following this paradigm, domain transfer approaches learn a prior Q-function from the related environments to prevent unsafe actions.…

Machine Learning · Computer Science 2025-04-29 Duc Kien Doan , Bang Giang Le , Viet Cuong Ta

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…

Machine Learning · Computer Science 2025-08-01 Yarden As , Bhavya Sukhija , Lenart Treven , Carmelo Sferrazza , Stelian Coros , Andreas Krause

We examine online safe multi-agent reinforcement learning using constrained Markov games in which agents compete by maximizing their expected total rewards under a constraint on expected total utilities. Our focus is confined to an episodic…

Machine Learning · Computer Science 2023-06-02 Dongsheng Ding , Xiaohan Wei , Zhuoran Yang , Zhaoran Wang , Mihailo R. Jovanović

Offline Preference-based Reinforcement Learning (PbRL) learns rewards and policies aligned with human preferences without the need for extensive reward engineering and direct interaction with human annotators. However, ensuring safety…

Artificial Intelligence · Computer Science 2025-12-24 Ze Gong , Pradeep Varakantham , Akshat Kumar

This paper proposes a safe reinforcement learning (RL) framework based on forward-invariance-induced action-space design. The control problem is cast as a Markov decision process, but instead of relying on runtime shielding or penalty-based…

Systems and Control · Electrical Eng. & Systems 2026-04-10 Chieh Tsai , Muhammad Junayed Hasan Zahed , Salim Hariri , Hossein Rastgoftar

We consider the problem of decision-making under uncertainty in an environment with safety constraints. Many business and industrial applications rely on real-time optimization to improve key performance indicators. In the case of unknown…

Machine Learning · Computer Science 2023-01-31 Buse Sibel Korkmaz , Marta Zagórowska , Mehmet Mercangöz

Safety is the priority concern when applying reinforcement learning (RL) algorithms to real-world control problems. While policy iteration provides a fundamental algorithm for standard RL, an analogous theoretical algorithm for safe RL…

Machine Learning · Computer Science 2025-03-14 Yujie Yang , Zhilong Zheng , Shengbo Eben Li , Wei Xu , Jingjing Liu , Xianyuan Zhan , Ya-Qin Zhang

Artificial intelligence (AI) systems possess significant potential to drive societal progress. However, their deployment often faces obstacles due to substantial safety concerns. Safe reinforcement learning (SafeRL) emerges as a solution to…

Artificial Intelligence · Computer Science 2024-10-08 Jiaming Ji , Borong Zhang , Jiayi Zhou , Xuehai Pan , Weidong Huang , Ruiyang Sun , Yiran Geng , Yifan Zhong , Juntao Dai , Yaodong Yang

Simulation-to-decision learning enables safe policy training in digital environments without risking real-world deployment, and has become essential in mission-critical domains such as supply chains and industrial systems. However,…

Machine Learning · Computer Science 2026-03-11 Hongyu Cao , Jinghan Zhang , Kunpeng Liu , Dongjie Wang , Feng Xia , Haifeng Chen , Xiaohua Hu , Yanjie Fu

Safety remains a central obstacle preventing widespread use of RL in the real world: learning new tasks in uncertain environments requires extensive exploration, but safety requires limiting exploration. We propose Recovery RL, an algorithm…

Safety is a crucial property of every robotic platform: any control policy should always comply with actuator limits and avoid collisions with the environment and humans. In reinforcement learning, safety is even more fundamental for…

Robotics · Computer Science 2023-03-02 Puze Liu , Kuo Zhang , Davide Tateo , Snehal Jauhri , Zhiyuan Hu , Jan Peters , Georgia Chalvatzaki

In high stakes environments, agents relying purely on imitation learning or reinforcement learning often struggle to avoid safety-critical errors during exploration. Existing reinforcement learning approaches for environments such as chess…

Machine Learning · Computer Science 2026-03-10 Prajit T Rajendran , Fabio Arnez , Huascar Espinoza , Agnes Delaborde , Chokri Mraidha

Autonomous exploration of obstacle-rich spaces requires strategies that ensure efficiency while guaranteeing safety against collisions with obstacles. This paper investigates a novel platform-agnostic reinforcement learning framework that…

Robotics · Computer Science 2025-11-20 Gabriele Calzolari , Vidya Sumathy , Christoforos Kanellakis , George Nikolakopoulos