English
Related papers

Related papers: Safe Value Functions

200 papers

Safe Reinforcement Learning (RL) plays an important role in applying RL algorithms to safety-critical real-world applications, addressing the trade-off between maximizing rewards and adhering to safety constraints. This work introduces a…

Robotics · Computer Science 2024-07-16 Fan Yang , Wenxuan Zhou , Zuxin Liu , Ding Zhao , David Held

Real-world reinforcement learning (RL) problems often demand that agents behave safely by obeying a set of designed constraints. We address the challenge of safe RL by coupling a safety guide based on model predictive control (MPC) with a…

Machine Learning · Computer Science 2022-03-30 Samuel Pfrommer , Tanmay Gautam , Alec Zhou , Somayeh Sojoudi

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

Reward design is a fundamental problem in reinforcement learning (RL). A misspecified or poorly designed reward can result in low sample efficiency and undesired behaviors. In this paper, we propose the idea of programmatic reward design,…

Machine Learning · Computer Science 2022-01-10 Weichao Zhou , Wenchao Li

Autonomous systems have witnessed a rapid increase in their capabilities, but it remains a challenge for them to perform tasks both effectively and safely. The fact that performance and safety can sometimes be competing objectives renders…

Systems and Control · Electrical Eng. & Systems 2024-12-04 Hao Wang , Adityaya Dhande , Somil Bansal

In the field of reinforcement learning (RL), agents are often tasked with solving a variety of problems differing only in their reward functions. In order to quickly obtain solutions to unseen problems with new reward functions, a popular…

Machine Learning · Computer Science 2023-06-16 Jacob Adamczyk , Volodymyr Makarenko , Argenis Arriojas , Stas Tiomkin , Rahul V. Kulkarni

Safe control methods are often intended to behave safely even in worst-case human uncertainties. However, humans may exploit such safety-first systems, which results in greater risk for everyone. Despite their significance, no prior work…

Human-Computer Interaction · Computer Science 2023-02-13 Zixuan Zhang , Maitham AL-Sunni , Haoming Jing , Hirokazu Shirado , Yorie Nakahira

Safe learning and optimization deals with learning and optimization problems that avoid, as much as possible, the evaluation of non-safe input points, which are solutions, policies, or strategies that cause an irrecoverable loss (e.g.,…

Machine Learning · Computer Science 2021-06-25 Youngmin Kim , Richard Allmendinger , Manuel López-Ibáñez

Reinforcement Learning (RL) uses rewards to guide learning, yet reward design is typically hand-crafted using heuristics that can be difficult to tune. We propose a Control Barrier Function (CBF)-informed reward design for Multi-Agent RL…

Robotics · Computer Science 2026-05-19 Jianye Xu , Bassam Alrifaee

In order to solve a task using reinforcement learning, it is necessary to first formalise the goal of that task as a reward function. However, for many real-world tasks, it is very difficult to manually specify a reward function that never…

Machine Learning · Computer Science 2024-12-13 Joar Skalse , Lucy Farnik , Sumeet Ramesh Motwani , Erik Jenner , Adam Gleave , Alessandro Abate

Penalty functions are widely used to enforce constraints in optimization problems and reinforcement leaning algorithms. Softplus and algebraic penalty functions are proposed to overcome the sensitivity of the Courant-Beltrami method to…

Optimization and Control · Mathematics 2021-07-12 Stefan Meili

This paper presents two new control approaches for guaranteed safety (remaining in a safe set) subject to actuator constraints (the control is in a convex polytope). The control signals are computed using real-time optimization, including…

Systems and Control · Electrical Eng. & Systems 2024-10-11 Pedram Rabiee , Jesse B. Hoagg

Despite recent successes in Reinforcement Learning, value-based methods often suffer from high variance hindering performance. In this paper, we illustrate this in a continuous control setting where state of the art methods perform poorly…

Machine Learning · Computer Science 2019-05-24 Pierre Thodoroff , Nishanth Anand , Lucas Caccia , Doina Precup , Joelle Pineau

The concept of the value-gradient is introduced and developed in the context of reinforcement learning. It is shown that by learning the value-gradients exploration or stochastic behaviour is no longer needed to find locally optimal…

Neural and Evolutionary Computing · Computer Science 2008-03-26 Michael Fairbank

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

We consider a one-period Kyle (1985) framework where the insider can be subject to a penalty if she trades. We establish existence and uniqueness of equilibrium for virtually any penalty function when noise is uniform. In equilibrium, the…

Trading and Market Microstructure · Quantitative Finance 2018-09-21 Sylvain Carré , Pierre Collin-Dufresne , Franck Gabriel

In recent years, the analysis of a control barrier function has received considerable attention because it is helpful for the safety-critical control required in many control application problems. While the extension of the analysis to a…

Optimization and Control · Mathematics 2024-04-18 Yuki Nishimura , Kenta Hoshino

In some agent designs like inverse reinforcement learning an agent needs to learn its own reward function. Learning the reward function and optimising for it are typically two different processes, usually performed at different stages. We…

Artificial Intelligence · Computer Science 2020-04-29 Stuart Armstrong , Jan Leike , Laurent Orseau , Shane Legg

The extremum value theorem for function spaces plays the central role in optimal control. It is known that computation of optimal control actions and policies is often prone to numerical errors which may be related to computability issues.…

Optimization and Control · Mathematics 2018-06-25 Pavel Osinenko , Stefan Streif

In many resource-limited optimal control problems, multiple constraints may be enforced that are jointly infeasible due to external factors such as subsystem failures, unexpected disturbances, or fuel limitations. In this manuscript, we…

Optimization and Control · Mathematics 2023-11-06 Natalia Pavlasek , Sarah H. Q. Li , Behçet Açıkmeşe , Meeko Oishi , Claus Danielson
‹ Prev 1 3 4 5 6 7 10 Next ›