中文
相关论文

相关论文: Disentangling Epistemic and Aleatoric Uncertainty …

200 篇论文

Representing and quantifying uncertainty in physical parameterisations is a central challenge in weather and climate modelling, and approaches are often developed separately for different timescales. Here, we introduce a unified framework…

大气与海洋物理 · 物理学 2025-12-01 Laura A. Mansfield , Hannah M. Christensen

Reinforcement learning (RL) often faces the challenges of uninformed search problems where the agent should explore without access to the domain knowledge such as characteristics of the environment or external rewards. To tackle these…

机器学习 · 计算机科学 2023-10-31 Daesol Cho , Seungjae Lee , H. Jin Kim

In many learning based control methodologies, learning the unknown dynamic model precedes the control phase, while the aim is to control the system such that it remains in some safe region of the state space. In this work, our aim is to…

机器学习 · 计算机科学 2021-05-14 Farhad Farokhi , Alex Leong , Iman Shames , Mohammad Zamani

Supervised masking approaches in the time-frequency domain aim to employ deep neural networks to estimate a multiplicative mask to extract clean speech. This leads to a single estimate for each input without any guarantees or measures of…

音频与语音处理 · 电气工程与系统科学 2023-05-16 Huajian Fang , Dennis Becker , Stefan Wermter , Timo Gerkmann

We address the problem of reinforcement learning in which observations may exhibit an arbitrary form of stochastic dependence on past observations and actions, i.e. environments more general than (PO)MDPs. The task for an agent is to attain…

机器学习 · 计算机科学 2009-12-30 Daniil Ryabko , Marcus Hutter

Reinforcement Learning (RL) remains a central optimisation framework in machine learning. Although RL agents can converge to optimal solutions, the definition of ``optimality'' depends on the environment's statistical properties. The…

机器学习 · 计算机科学 2026-01-14 Bert Verbruggen , Arne Vanhoyweghen , Vincent Ginis

Fairness-aware learning aims at satisfying various fairness constraints in addition to the usual performance criteria via data-driven machine learning techniques. Most of the research in fairness-aware learning employs the setting of…

机器学习 · 计算机科学 2022-05-23 Pratik Gajane , Akrati Saxena , Maryam Tavakol , George Fletcher , Mykola Pechenizkiy

The aim of Reinforcement Learning (RL) in real-world applications is to create systems capable of making autonomous decisions by learning from their environment through trial and error. This paper emphasizes the importance of reward…

机器学习 · 计算机科学 2024-12-31 Sinan Ibrahim , Mostafa Mostafa , Ali Jnadi , Hadi Salloum , Pavel Osinenko

Trustworthy ML systems should not only return accurate predictions, but also a reliable representation of their uncertainty. Bayesian methods are commonly used to quantify both aleatoric and epistemic uncertainty, but alternative…

人工智能 · 计算机科学 2024-09-11 Mira Jürgens , Nis Meinert , Viktor Bengs , Eyke Hüllermeier , Willem Waegeman

This paper proposes a suite of rationality measures and associated theory for reinforcement learning agents, a property increasingly critical yet rarely explored. We define an action in deployment to be perfectly rational if it maximises…

机器学习 · 计算机科学 2026-05-05 Kejiang Qian , Amos Storkey , Fengxiang He

Reinforcement learning (RL) is one of the active fields in machine learning, demonstrating remarkable potential in tackling real-world challenges. Despite its promising prospects, this methodology has encountered with issues and challenges,…

机器学习 · 计算机科学 2024-11-21 Alireza Rashidi Laleh , Majid Nili Ahmadabadi

Off-policy learning plays a pivotal role in optimizing and evaluating policies prior to the online deployment. However, during the real-time serving, we observe varieties of interventions and constraints that cause inconsistency between the…

机器学习 · 计算机科学 2022-03-01 Da Xu , Yuting Ye , Chuanwei Ruan , Bo Yang

Model-free reinforcement learning based methods such as Proximal Policy Optimization, or Q-learning typically require thousands of interactions with the environment to approximate the optimum controller which may not always be feasible in…

机器学习 · 计算机科学 2019-05-16 Narendra Patwardhan , Zequn Wang

To further improve the learning efficiency and performance of reinforcement learning (RL), in this paper we propose a novel uncertainty-aware model-based RL (UA-MBRL) framework, and then implement and validate it in autonomous driving under…

机器人学 · 计算机科学 2021-07-06 Jingda Wu , Zhiyu Huang , Chen Lv

From out-competing grandmasters in chess to informing high-stakes healthcare decisions, emerging methods from artificial intelligence are increasingly capable of making complex and strategic decisions in diverse, high-dimensional, and…

计算机与社会 · 计算机科学 2024-03-05 Melissa Chapman , Lily Xu , Marcus Lapeyrolerie , Carl Boettiger

Reinforcement learning (RL) offers a compelling data-driven paradigm for synthesizing controllers for complex systems when accurate physical models are unavailable; however, most existing control-oriented RL methods assume stationarity and,…

机器学习 · 计算机科学 2026-04-22 Austin Coursey , Abel Diaz-Gonzalez , Marcos Quinones-Grueiro , Gautam Biswas

Reinforcement learning provides an appealing framework for robotic control due to its ability to learn expressive policies purely through real-world interaction. However, this requires addressing real-world constraints and avoiding…

机器人学 · 计算机科学 2024-05-09 Kyle Stachowicz , Sergey Levine

Offline reinforcement learning (RL) is suitable for safety-critical domains where online exploration is too costly or dangerous. In such safety-critical settings, decision-making should take into consideration the risk of catastrophic…

机器学习 · 计算机科学 2023-10-31 Marc Rigter , Bruno Lacerda , Nick Hawes

Prioritized experience replay, which improves sample efficiency by selecting relevant transitions to update parameter estimates, is a crucial component of contemporary value-based deep reinforcement learning models. Typically, transitions…

机器学习 · 计算机科学 2025-06-12 Rodrigo Carrasco-Davis , Sebastian Lee , Claudia Clopath , Will Dabney

As instruction-tuned large language models (LLMs) evolve, aligning pretrained foundation models presents increasing challenges. Existing alignment strategies, which typically leverage diverse and high-quality data sources, often overlook…

计算与语言 · 计算机科学 2024-06-10 Yikun Wang , Rui Zheng , Liang Ding , Qi Zhang , Dahua Lin , Dacheng Tao