中文
相关论文

相关论文: Counterfactually Safe Reinforcement Learning

200 篇论文

This paper considers the problem of learning safe policies in the context of reinforcement learning (RL). In particular, we consider the notion of probabilistic safety. This is, we aim to design policies that maintain the state of the…

机器学习 · 计算机科学 2023-04-20 Weiqin Chen , Dharmashankar Subramanian , Santiago Paternain

Searching the space of policies directly for the optimal policy has been one popular method for solving partially observable reinforcement learning problems. Typically, with each change of the target policy, its value is estimated from the…

人工智能 · 计算机科学 2007-05-23 Leonid Peshkin , Christian R. Shelton

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…

机器人学 · 计算机科学 2023-07-28 Brian Angulo , Gregory Gorbov , Aleksandr Panov , Konstantin Yakovlev

We study automated intrusion prevention using reinforcement learning. In a novel approach, we formulate the problem of intrusion prevention as an optimal stopping problem. This formulation allows us insight into the structure of the optimal…

人工智能 · 计算机科学 2024-04-23 Kim Hammar , Rolf Stadler

Offline reinforcement learning algorithms still lack trust in practice due to the risk that the learned policy performs worse than the original policy that generated the dataset or behaves in an unexpected way that is unfamiliar to the…

机器学习 · 计算机科学 2023-01-26 Phillip Swazinna , Steffen Udluft , Thomas Runkler

Safety is a primary concern when applying reinforcement learning to real-world control tasks, especially in the presence of external disturbances. However, existing safe reinforcement learning algorithms rarely account for external…

机器学习 · 计算机科学 2023-10-12 Zeyang Li , Chuxiong Hu , Shengbo Eben Li , Jia Cheng , Yunan Wang

The primary goal of reinforcement learning is to develop decision-making policies that prioritize optimal performance without considering risk or safety. In contrast, safe reinforcement learning aims to mitigate or avoid unsafe states. This…

机器学习 · 计算机科学 2024-09-13 Zahra Shahrooei , Ali Baheri

The inputs and preferences of human users are important considerations in situations where these users interact with autonomous cyber or cyber-physical systems. In these scenarios, one is often interested in aligning behaviors of the system…

机器学习 · 计算机科学 2021-04-02 Bhaskar Ramasubramanian , Luyao Niu , Andrew Clark , Radha Poovendran

We propose a framework for ensuring safe behavior of a reinforcement learning agent when the reward function may be difficult to specify. In order to do this, we rely on the existence of demonstrations from expert policies, and we provide a…

机器学习 · 计算机科学 2018-11-22 Jessie Huang , Fa Wu , Doina Precup , Yang Cai

Conventional reinforcement learning (RL) methods can successfully solve a wide range of sequential decision problems. However, learning policies that can generalize predictably across multiple tasks in a setting with non-Markovian reward…

机器学习 · 计算机科学 2024-06-04 Guillermo Infante , David Kuric , Anders Jonsson , Vicenç Gómez , Herke van Hoof

Counterfactual thinking describes a psychological phenomenon that people re-infer the possible results with different solutions about things that have already happened. It helps people to gain more experience from mistakes and thus to…

机器学习 · 计算机科学 2019-08-19 Yue Wang , Yao Wan , Chenwei Zhang , Lixin Cui , Lu Bai , Philip S. Yu

Conventional methods for query autocompletion aim to predict which completed query a user will select from a list. A shortcoming of this approach is that users often do not know which query will provide the best retrieval performance on the…

信息检索 · 计算机科学 2022-04-26 Adam Block , Rahul Kidambi , Daniel N. Hill , Thorsten Joachims , Inderjit S. Dhillon

Algorithmic risk assessments are increasingly used to help humans make decisions in high-stakes settings, such as medicine, criminal justice and education. In each of these cases, the purpose of the risk assessment tool is to inform…

机器学习 · 统计学 2020-01-13 Amanda Coston , Alan Mishler , Edward H. Kennedy , Alexandra Chouldechova

The problem of reinforcement learning is considered where the environment or the model undergoes a change. An algorithm is proposed that an agent can apply in such a problem to achieve the optimal long-time discounted reward. The algorithm…

系统与控制 · 电气工程与系统科学 2023-04-25 Wuxia Chen , Taposh Banerjee , Jemin George , Carl Busart

In this paper, we present an online reinforcement learning algorithm for constrained Markov decision processes with a safety constraint. Despite the necessary attention of the scientific community, considering stochastic stopping time, the…

机器学习 · 计算机科学 2024-03-26 Abhijit Mazumdar , Rafal Wisniewski , Manuela L. Bujorianu

Reinforcement learning optimizes policies for expected cumulative reward. Need the supervision be so narrow? Reward is delayed and sparse for many tasks, making it a difficult and impoverished signal for end-to-end optimization. To augment…

机器学习 · 计算机科学 2017-03-10 Evan Shelhamer , Parsa Mahmoudieh , Max Argus , Trevor Darrell

Optimal designs are usually model-dependent and likely to be sub-optimal if the postulated model is not correctly specified. In practice, it is common that a researcher has a list of candidate models at hand and a design has to be found…

统计理论 · 数学 2023-03-29 Mingyao Ai , Holger Dette , Zhengfu Liu , Jun Yu

Autonomous vehicles with a self-evolving ability are expected to cope with unknown scenarios in the real-world environment. Take advantage of trial and error mechanism, reinforcement learning is able to self evolve by learning the optimal…

机器人学 · 计算机科学 2024-08-23 Shuo Yang , Liwen Wang , Yanjun Huang , Hong Chen

Various methods for solving the inverse reinforcement learning (IRL) problem have been developed independently in machine learning and economics. In particular, the method of Maximum Causal Entropy IRL is based on the perspective of entropy…

机器学习 · 计算机科学 2021-03-05 Navyata Sanghvi , Shinnosuke Usami , Mohit Sharma , Joachim Groeger , Kris Kitani

In this work we introduce reinforcement learning techniques for solving lexicographic multi-objective problems. These are problems that involve multiple reward signals, and where the goal is to learn a policy that maximises the first reward…

机器学习 · 计算机科学 2022-12-29 Joar Skalse , Lewis Hammond , Charlie Griffin , Alessandro Abate