English
Related papers

Related papers: Safe Value Functions

200 papers

Reward functions are notoriously difficult to specify, especially for tasks with complex goals. Reward learning approaches attempt to infer reward functions from human feedback and preferences. Prior works on reward learning have mainly…

Machine Learning · Computer Science 2023-01-11 Lev McKinney , Yawen Duan , David Krueger , Adam Gleave

As the complexity of control systems increases, the need for systematic methods to guarantee their efficacy grows as well. However, direct testing of these systems is oftentimes costly, difficult, or impractical. As a result, the test and…

Systems and Control · Electrical Eng. & Systems 2021-09-10 Prithvi Akella , Ugo Rosolia , Aaron D. Ames

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 study stochastic systems characterized by difference inclusions. Such stochastic differential inclusions are defined by set-valued maps involving the current state and stochastic input. For such systems, we investigate the problem of…

Optimization and Control · Mathematics 2025-08-29 Masoumeh Ghanbarpour , Sriram Sankaranarayanan

In the field of safe reinforcement learning (RL), finding a balance between satisfying safety constraints and optimizing reward performance presents a significant challenge. A key obstacle in this endeavor is the estimation of safety…

Machine Learning · Computer Science 2024-06-14 Zhepeng Cen , Yihang Yao , Zuxin Liu , Ding Zhao

Solving tasks in Reinforcement Learning is no easy feat. As the goal of the agent is to maximize the accumulated reward, it often learns to exploit loopholes and misspecifications in the reward signal resulting in unwanted behavior. While…

Machine Learning · Computer Science 2018-12-27 Chen Tessler , Daniel J. Mankowitz , Shie Mannor

Learning about many things can provide numerous benefits to a reinforcement learning system. For example, learning many auxiliary value functions, in addition to optimizing the environmental reward, appears to improve both exploration and…

Machine Learning · Computer Science 2020-08-25 Cam Linke , Nadia M. Ady , Martha White , Thomas Degris , Adam White

In this paper, stability and sensitivity properties of a class of parametric constrained optimization problem, whose feasible region is defined by a set-valued inclusion, are investigated through the associated optimal value function.…

Optimization and Control · Mathematics 2024-12-06 Amos Uderzo

We consider the problem of learning control policies that optimize a reward function while satisfying constraints due to considerations of safety, fairness, or other costs. We propose a new algorithm, Projection-Based Constrained Policy…

Machine Learning · Computer Science 2020-10-08 Tsung-Yen Yang , Justinian Rosca , Karthik Narasimhan , Peter J. Ramadge

Adaptive optimal control using value iteration (VI) initiated from a stabilizing policy is theoretically analyzed in various aspects including the continuity of the result, the stability of the system operated using any single/constant…

Systems and Control · Computer Science 2015-05-18 Ali Heydari

Reinforcement learning (RL) is increasingly used to personalize instruction in intelligent tutoring systems, yet the field lacks a formal framework for defining and evaluating pedagogical safety. We introduce a four-layer model of…

Artificial Intelligence · Computer Science 2026-04-07 Oluseyi Olukola , Nick Rahimi

Model Predictive Control (MPC) can be applied to safety-critical control problems, providing closed-loop safety and performance guarantees. Implementation of MPC controllers requires solving an optimization problem at every sampling…

Systems and Control · Electrical Eng. & Systems 2025-03-27 Nicolas Chatzikiriakos , Kim P. Wabersich , Felix Berkel , Patricia Pauli , Andrea Iannelli

Accurate quantification of safety is essential for the design of autonomous systems. In this paper, we present a methodology to characterize the exact probabilities associated with invariance and recovery in safe control. We consider a…

Optimization and Control · Mathematics 2021-04-22 Albert Chern , Xiang Wang , Abhiram Iyer , Yorie Nakahira

Although learning-based methods have great potential for robotics, one concern is that a robot that updates its parameters might cause large amounts of damage before it learns the optimal policy. We formalize the idea of safe learning in a…

Robotics · Computer Science 2017-05-17 David Held , Zoe McCarthy , Michael Zhang , Fred Shentu , Pieter Abbeel

This paper proposes an optimization with penalty-based feedback design framework for safe stabilization of control affine systems. Our starting point is the availability of a control Lyapunov function (CLF) and a control barrier function…

Optimization and Control · Mathematics 2022-07-26 Pol Mestres , Jorge Cortés

We characterize the value of swing contracts in continuous time as the unique viscosity solution of a Hamilton-Jacobi-Bellman equation with suitable boundary conditions. The case of contracts with penalties is straightforward, and in that…

Optimization and Control · Mathematics 2013-07-05 M. Basei , A. Cesaroni , T. Vargiolu

In the trial-and-error mechanism of reinforcement learning (RL), a notorious contradiction arises when we expect to learn a safe policy: how to learn a safe policy without enough data and prior model about the dangerous region? Existing…

Machine Learning · Computer Science 2021-11-29 Haitong Ma , Changliu Liu , Shengbo Eben Li , Sifa Zheng , Wenchao Sun , Jianyu Chen

Decision support systems (e.g., for ecological conservation) and autonomous systems (e.g., adaptive controllers in smart cities) start to be deployed in real applications. Although their operations often impact many users or stakeholders,…

Machine Learning · Computer Science 2019-07-25 Paul Weng

Enforcing safety for dynamical systems is challenging, since it requires constraint satisfaction along trajectory predictions. Equivalent control constraints can be computed in the form of sets that enforce positive invariance, and can thus…

Systems and Control · Electrical Eng. & Systems 2021-05-19 Pierre-François Massiani , Steve Heim , Sebastian Trimpe

The control barrier function (CBF) has become a fundamental tool in safety-critical systems design since its invention. Typically, the quadratic optimization framework is employed to accommodate CBFs, control Lyapunov functions (CLFs),…

Optimization and Control · Mathematics 2026-03-17 Junjun Xie , Liang Hu , Jiahu Qin , Jun Yang , Huijun Gao