中文
相关论文

相关论文: Incorporating System-level Safety Requirements in …

200 篇论文

Reward shaping has been applied widely to accelerate Reinforcement Learning (RL) agents' training. However, a principled way of designing effective reward shaping functions, especially for complex continuous control problems, remains…

机器学习 · 计算机科学 2026-02-12 Mateo Juliani , Mingxuan Li , Elias Bareinboim

In standard reinforcement learning (RL), a learning agent seeks to optimize the overall reward. However, many key aspects of a desired behavior are more naturally expressed as constraints. For instance, the designer may want to limit the…

机器学习 · 计算机科学 2021-01-29 Sobhan Miryoosefi , Kianté Brantley , Hal Daumé , Miroslav Dudik , Robert Schapire

The alignment of autonomous agents with human values is a pivotal challenge when deploying these agents within physical environments, where safety is an important concern. However, defining the agent's objective as a reward and/or cost…

机器学习 · 计算机科学 2023-12-15 Mattijs Baert , Sam Leroux , Pieter Simoens

Reinforcement learning plays a crucial role in vehicle control by guiding agents to learn optimal control strategies through designing or learning appropriate reward signals. However, in vehicle control applications, rewards typically need…

机器学习 · 计算机科学 2025-04-21 Jielong Yang , Daoyuan Huang

Many real-world systems problems require reasoning about the long term consequences of actions taken to configure and manage the system. These problems with delayed and often sequentially aggregated reward, are often inherently…

机器学习 · 计算机科学 2019-09-06 Ameer Haj-Ali , Nesreen K. Ahmed , Ted Willke , Joseph Gonzalez , Krste Asanovic , Ion Stoica

Reinforcement learning (RL) has been successfully applied to a variety of robotics applications, where it outperforms classical methods. However, the safety aspect of RL and the transfer to the real world remain an open challenge. A…

机器人学 · 计算机科学 2025-04-21 Murad Dawood , Ahmed Shokry , Maren Bennewitz

Testing is essential for verifying and validating control designs, especially in safety-critical applications. In particular, the control system governing an automated driving vehicle must be proven reliable enough for its acceptance on the…

系统与控制 · 电气工程与系统科学 2023-09-11 Mengjia Zhu , Alberto Bemporad , Maximilian Kneissl , Hasan Esen

The incorporation of advanced sensors and machine learning techniques has enabled modern manufacturing enterprises to perform data-driven classification-based anomaly detection based on the sensor data collected in manufacturing processes.…

机器学习 · 计算机科学 2024-11-19 Yuxuan Li , Tianxin Xie , Chenang Liu , Zhangyue Shi

Neural Networks are being integrated into safety critical systems, e.g., perception systems for autonomous vehicles, which require trained networks to perform safely in novel scenarios. It is challenging to verify neural networks because…

机器学习 · 计算机科学 2019-12-23 Molly O'Brien , William Goble , Greg Hager , Julia Bukowski

In this work, we propose a self-improving artificial intelligence system to enhance the safety performance of reinforcement learning (RL)-based autonomous driving (AD) agents using black-box verification methods. RL algorithms have become…

人工智能 · 计算机科学 2025-07-21 Resul Dagdanov , Halil Durmus , Nazim Kemal Ure

Performance evaluations are critical for quantifying algorithmic advances in reinforcement learning. Recent reproducibility analyses have shown that reported performance results are often inconsistent and difficult to replicate. In this…

机器学习 · 计算机科学 2020-08-14 Scott M. Jordan , Yash Chandak , Daniel Cohen , Mengxue Zhang , Philip S. Thomas

We propose the Linearly Adaptive Cross Entropy Loss function. This is a novel measure derived from the information theory. In comparison to the standard cross entropy loss function, the proposed one has an additional term that depends on…

机器学习 · 计算机科学 2025-07-16 Jae Wan Shim

Reinforcement Learning (RL) has proven highly effective in aligning Large Language Models (LLMs) with human preferences. Typical RL methods optimize under an overall sequence reward, which can lead to a suboptimal learning process. This…

机器学习 · 计算机科学 2025-02-26 Yanshi Li , Shaopan Xiong , Gengru Chen , Xiaoyang Li , Yijia Luo , Xingyuan Bu , Yingshui Tan , Wenbo Su , Bo Zheng

This paper presents an approach for data-driven policy refinement in reinforcement learning, specifically designed for safety-critical applications. Our methodology leverages the strengths of data-driven optimization and reinforcement…

机器学习 · 计算机科学 2023-05-16 Ali Baheri

We propose a novel Reinforcement Learning model for discrete environments, which is inherently interpretable and supports the discovery of deep subgoal hierarchies. In the model, an agent learns information about environment in the form of…

人工智能 · 计算机科学 2022-02-16 Alexander Demin , Denis Ponomaryov

Precise robotic manipulation skills are desirable in many industrial settings, reinforcement learning (RL) methods hold the promise of acquiring these skills autonomously. In this paper, we explicitly consider incorporating operational…

机器人学 · 计算机科学 2019-03-21 Jianlan Luo , Eugen Solowjow , Chengtao Wen , Juan Aparicio Ojea , Alice M. Agogino , Aviv Tamar , Pieter Abbeel

The main focus of this paper is on enhancement of two types of game-theoretic learning algorithms: log-linear learning and reinforcement learning. The standard analysis of log-linear learning needs a highly structured environment, i.e.…

机器学习 · 计算机科学 2018-09-19 Mohammadhosein Hasanbeig , Lacra Pavel

The success of Reinforcement Learning (RL) heavily relies on the ability to learn robust representations from the observations of the environment. In most cases, the representations learned purely by the reinforcement learning loss can…

机器学习 · 计算机科学 2024-02-12 Somjit Nath , Rushiv Arora , Samira Ebrahimi Kahou

Standard regression techniques, while powerful, are often constrained by predefined, differentiable loss functions such as mean squared error. These functions may not fully capture the desired behavior of a system, especially when dealing…

机器学习 · 计算机科学 2025-08-04 Yongchao Huang

Goals for reinforcement learning problems are typically defined through hand-specified rewards. To design such problems, developers of learning algorithms must inherently be aware of what the task goals are, yet we often require agents to…

机器学习 · 计算机科学 2018-03-29 Ashley D. Edwards , Laura Downs , James C. Davidson
‹ 上一页 1 8 9 10 下一页 ›