English
Related papers

Related papers: Safety-Constrained Reinforcement Learning with Pos…

200 papers

Reinforcement learning can enable complex, adaptive behavior to be learned automatically for autonomous robotic platforms. However, practical deployment of reinforcement learning methods must contend with the fact that the training process…

Machine Learning · Computer Science 2017-02-07 Gregory Kahn , Adam Villaflor , Vitchyr Pong , Pieter Abbeel , Sergey Levine

Training Reinforcement Learning (RL) agents in high-stakes applications might be too prohibitive due to the risk associated to exploration. Thus, the agent can only use data previously collected by safe policies. While previous work…

Machine Learning · Computer Science 2021-02-11 Núria Armengol Urpí , Sebastian Curi , Andreas Krause

Ensuring safety is a critical challenge in applying Reinforcement Learning (RL) to real-world scenarios. Constrained Reinforcement Learning (CRL) addresses this by maximizing returns under predefined constraints, typically formulated as the…

Machine Learning · Computer Science 2026-01-21 Shiqing Gao , Yihang Zhou , Shuai Shao , Haoyu Luo , Yiheng Bing , Jiaxin Ding , Luoyi Fu , Xinbing Wang

Neural networks have recently become popular for a wide variety of uses, but have seen limited application in safety-critical domains such as robotics near and around humans. This is because it remains an open challenge to train a neural…

Machine Learning · Computer Science 2021-07-19 Long Kiu Chung , Adam Dai , Derek Knowles , Shreyas Kousik , Grace X. Gao

We address the problem of coordination and control of Connected and Automated Vehicles (CAVs) in the presence of imperfect observations in mixed traffic environment. A commonly used approach is learning-based decision-making, such as…

Robotics · Computer Science 2024-09-25 Zhili Zhang , H M Sabbir Ahmad , Ehsan Sabouni , Yanchao Sun , Furong Huang , Wenchao Li , Fei Miao

Robust Markov Decision Processes (RMDPs) have received significant research interest, offering an alternative to standard Markov Decision Processes (MDPs) that often assume fixed transition probabilities. RMDPs address this by optimizing…

Machine Learning · Computer Science 2024-05-06 Xinyi Ni , Lifeng Lai

Designing provably safe control is a core problem in trustworthy autonomy. However, most prior work in this regard assumes either that the system dynamics are known or deterministic, or that the state and action space are finite,…

Robotics · Computer Science 2026-02-04 Xinhang Ma , Junlin Wu , Yiannis Kantaros , Yevgeniy Vorobeychik

It is quite challenging to ensure the safety of reinforcement learning (RL) agents in an unknown and stochastic environment under hard constraints that require the system state not to reach certain specified unsafe regions. Many popular…

Systems and Control · Electrical Eng. & Systems 2023-06-14 Yixuan Wang , Simon Sinong Zhan , Ruochen Jiao , Zhilu Wang , Wanxin Jin , Zhuoran Yang , Zhaoran Wang , Chao Huang , Qi Zhu

Many safety-critical control systems must operate under latent uncertainty that sensors cannot directly resolve at decision time. Such uncertainty, arising from unknown physical properties, exogenous disturbances, or unobserved environment…

Systems and Control · Electrical Eng. & Systems 2026-04-07 Clinton Enwerem , John S. Baras , Calin Belta

Safety is one of the main challenges in applying reinforcement learning to realistic environmental tasks. To ensure safety during and after training process, existing methods tend to adopt overly conservative policy to avoid unsafe…

Machine Learning · Computer Science 2023-06-27 Xiao Zhang , Hai Zhang , Hongtu Zhou , Chang Huang , Di Zhang , Chen Ye , Junqiao Zhao

We consider the problem of risk-sensitive motion planning in the presence of randomly moving obstacles. To this end, we adopt a model predictive control (MPC) scheme and pose the obstacle avoidance constraint in the MPC problem as a…

Systems and Control · Electrical Eng. & Systems 2021-07-20 Anushri Dixit , Mohamadreza Ahmadi , Joel W. Burdick

We consider an online stochastic game with risk-averse agents whose goal is to learn optimal decisions that minimize the risk of incurring significantly high costs. Specifically, we use the Conditional Value at Risk (CVaR) as a risk measure…

Machine Learning · Computer Science 2022-06-17 Zifan Wang , Yi Shen , Michael M. Zavlanos

Reinforcement Learning (RL) has proven largely effective in obtaining stable locomotion gaits for legged robots. However, designing control algorithms which can robustly navigate unseen environments with obstacles remains an ongoing problem…

Robotics · Computer Science 2025-03-17 Jose-Luis Holgado-Alvarez , Aryaman Reddi , Carlo D'Eramo

Safety is an essential component for deploying reinforcement learning (RL) algorithms in real-world scenarios, and is critical during the learning process itself. A natural first approach toward safe RL is to manually specify constraints on…

Machine Learning · Computer Science 2020-10-29 Krishnan Srinivasan , Benjamin Eysenbach , Sehoon Ha , Jie Tan , Chelsea Finn

Socially aware navigation is a fast-evolving research area in robotics that enables robots to move within human environments while adhering to the implicit human social norms. The advent of Deep Reinforcement Learning (DRL) has accelerated…

Robotics · Computer Science 2025-12-02 Ibrahim Khalil Kabir , Muhammad Faizan Mysorewala

The need for a systematic approach to risk assessment has increased in recent years due to the ubiquity of autonomous systems that alter our day-to-day experiences and their need for safety, e.g., for self-driving vehicles, mobile service…

We present a novel Deep Reinforcement Learning (DRL) based policy to compute dynamically feasible and spatially aware velocities for a robot navigating among mobile obstacles. Our approach combines the benefits of the Dynamic Window…

Robotics · Computer Science 2020-11-30 Utsav Patel , Nithish Kumar , Adarsh Jagan Sathyamoorthy , Dinesh Manocha

While reinforcement learning algorithms have had great success in the field of autonomous navigation, they cannot be straightforwardly applied to the real autonomous systems without considering the safety constraints. The later are crucial…

Robotics · Computer Science 2023-07-28 Brian Angulo , Gregory Gorbov , Aleksandr Panov , Konstantin Yakovlev

Safe reinforcement learning (RL) trains a policy to maximize the task reward while satisfying safety constraints. While prior works focus on the performance optimality, we find that the optimal solutions of many safe RL problems are not…

Machine Learning · Computer Science 2023-03-03 Zuxin Liu , Zijian Guo , Zhepeng Cen , Huan Zhang , Jie Tan , Bo Li , Ding Zhao

The conditional value-at-risk (CVaR) is a useful risk measure in fields such as machine learning, finance, insurance, energy, etc. When measuring very extreme risk, the commonly used CVaR estimation method of sample averaging does not work…

Methodology · Statistics 2021-03-10 Dylan Troop , Frédéric Godin , Jia Yuan Yu