English
Related papers

Related papers: Model-based Chance-Constrained Reinforcement Learn…

200 papers

We study the problem of safe offline reinforcement learning (RL), the goal is to learn a policy that maximizes long-term reward while satisfying safety constraints given only offline data, without further interaction with the environment.…

Machine Learning · Computer Science 2022-04-11 Haoran Xu , Xianyuan Zhan , Xiangyu Zhu

Ensuring safety of nonlinear systems under model uncertainty and external disturbances is crucial, especially for real-world control tasks. Predictive methods such as robust model predictive control (RMPC) require solving nonconvex…

Systems and Control · Electrical Eng. & Systems 2023-11-14 Zeyang Li , Chuxiong Hu , Weiye Zhao , Changliu Liu

Balancing reward and safety in constrained reinforcement learning remains challenging due to poor generalization from sharp value minima and inadequate handling of heavy-tailed risk distribution. We introduce Safe Langevin Soft Actor-Critic…

Machine Learning · Computer Science 2026-02-03 Mahesh Keswani , Samyak Jain , Raunak P. Bhattacharyya

Safety is a primary challenge in real-world reinforcement learning (RL). Formulating safety requirements as state-wise constraints has become a prominent paradigm. Handling state-wise constraints with the Lagrangian method requires a…

Machine Learning · Computer Science 2026-05-04 Jiaming Zhang , Yujie Yang , Yao Lyu , Shengbo Eben Li , Liping Zhang

The goal of the inverse reinforcement learning (IRL) problem is to recover the reward functions from expert demonstrations. However, the IRL problem like any ill-posed inverse problem suffers the congenital defect that the policy may be…

Machine Learning · Computer Science 2022-09-26 Ce Ju

For real-world deployments, it is critical to allow robots to navigate in complex environments autonomously. Traditional methods usually maintain an internal map of the environment, and then design several simple rules, in conjunction with…

Robotics · Computer Science 2021-04-16 Yuanyang Zhu , Zhi Wang , Chunlin Chen , Daoyi Dong

Reinforcement learning (RL) methods have demonstrated their efficiency in simulation environments. However, many applications for which RL offers great potential, such as autonomous driving, are also safety critical and require a certified…

Systems and Control · Electrical Eng. & Systems 2021-01-19 Kim P. Wabersich , Lukas Hewing , Andrea Carron , Melanie N. Zeilinger

While Group Relative Policy Optimization (GRPO) has emerged as a scalable framework for critic-free policy learning, extending it to settings with explicit behavioral constraints remains underexplored. We introduce Constrained GRPO, a…

Machine Learning · Computer Science 2026-02-09 Roger Girgis , Rodrigue de Schaetzen , Luke Rowe , Azalée Robitaille , Christopher Pal , Liam Paull

Constrained optimization provides a common framework for dealing with conflicting objectives in reinforcement learning (RL). In most of these settings, the objectives (and constraints) are expressed though the expected accumulated reward.…

Machine Learning · Computer Science 2025-12-03 Jane H. Lee , Baturay Saglam , Spyridon Pougkakiotis , Amin Karbasi , Dionysis Kalogerias

Reinforcement learning (RL) has become a predominant technique to align language models (LMs) with human preferences or promote outputs which are deemed to be desirable by a given reward function. Standard RL approaches optimize average…

Machine Learning · Computer Science 2025-10-27 Stephen Zhao , Aidan Li , Rob Brekelmans , Roger Grosse

Classical reinforcement learning (RL) techniques are generally concerned with the design of decision-making policies driven by the maximisation of the expected outcome. Nevertheless, this approach does not take into consideration the…

Machine Learning · Computer Science 2023-01-02 Thibaut Théate , Damien Ernst

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…

Differential Dynamic Programming (DDP) has become a well established method for unconstrained trajectory optimization. Despite its several applications in robotics and controls however, a widely successful constrained version of the…

Optimization and Control · Mathematics 2020-05-05 Yuichiro Aoyama , George Boutselis , Akash Patel , Evangelos A. Theodorou

This paper introduces a flight envelope protection algorithm on a longitudinal axis that leverages reinforcement learning (RL). By considering limits on variables such as angle of attack, load factor, and pitch rate, the algorithm…

Systems and Control · Electrical Eng. & Systems 2024-06-13 Akin Catak , Ege C. Altunkaya , Mustafa Demir , Emre Koyuncu , Ibrahim Ozkol

Imitation learning (IL) is a simple and powerful way to use high-quality human driving data, which can be collected at scale, to produce human-like behavior. However, policies based on imitation learning alone often fail to sufficiently…

Reinforcement Learning (RL) has recently impressed the world with stunning results in various applications. While the potential of RL is now well-established, many critical aspects still need to be tackled, including safety and stability…

Systems and Control · Electrical Eng. & Systems 2024-09-23 Mario Zanon , Sébastien Gros

Safe reinforcement learning has traditionally relied on predefined constraint functions to ensure safety in complex real-world tasks, such as autonomous driving. However, defining these functions accurately for varied tasks is a persistent…

Machine Learning · Computer Science 2025-01-31 Se-Wook Yoo , Seung-Woo Seo

Lagrangian systems represent a wide range of robotic systems, including manipulators, wheeled and legged robots, and quadrotors. Inverse dynamics control and feedforward linearization techniques are typically used to convert the complex…

Robotics · Computer Science 2018-09-13 Mohamed K. Helwa , Adam Heins , Angela P. Schoellig

In safe offline reinforcement learning (RL), the objective is to develop a policy that maximizes cumulative rewards while strictly adhering to safety constraints, utilizing only offline data. Traditional methods often face difficulties in…

Machine Learning · Computer Science 2026-02-11 Prajwal Koirala , Zhanhong Jiang , Soumik Sarkar , Cody Fleming

We propose a new splitting and successively solving augmented Lagrangian (SSAL) method for solving an optimization problem with both semicontinuous variables and a cardinality constraint. This optimization problem arises in several contexts…

Optimization and Control · Mathematics 2015-06-16 Yanqin Bai , Renli Liang , Zhouwang Yang