中文
相关论文

相关论文: Sample-Efficient Reinforcement Learning in the Pre…

200 篇论文

The sim-to-real gap, which represents the disparity between training and testing environments, poses a significant challenge in reinforcement learning (RL). A promising approach to addressing this challenge is distributionally robust RL,…

机器学习 · 计算机科学 2024-11-05 Miao Lu , Han Zhong , Tong Zhang , Jose Blanchet

One of the key approaches to save samples in reinforcement learning (RL) is to use knowledge from an approximate model such as its simulator. However, how much does an approximate model help to learn a near-optimal policy of the true…

机器学习 · 计算机科学 2020-07-15 Fei Feng , Wotao Yin , Lin F. Yang

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

Empowered by deep neural networks, deep reinforcement learning (DRL) has demonstrated tremendous empirical successes in various domains, including games, health care, and autonomous driving. Despite these advancements, DRL is still…

机器学习 · 计算机科学 2024-01-22 Dayang Liang , Yaru Zhang , Yunlong Liu

The current thesis aims to explore the reinforcement learning field and build on existing methods to produce improved ones to tackle the problem of learning in high-dimensional and complex environments. It addresses such goals by…

机器学习 · 计算机科学 2024-03-26 Ayoub Ghriss , Masashi Sugiyama , Alessandro Lazaric

In the standard data analysis framework, data is collected (once and for all), and then data analysis is carried out. However, with the advancement of digital technology, decision-makers constantly analyze past data and generate new data…

机器学习 · 统计学 2024-12-25 Jin Li , Ye Luo , Zigan Wang , Xiaowei Zhang

A common setting of reinforcement learning (RL) is a Markov decision process (MDP) in which the environment is a stochastic discrete-time dynamical system. Whereas MDPs are suitable in such applications as video-games or puzzles, physical…

机器人学 · 计算机科学 2022-11-29 Pavel Osinenko , Dmitrii Dobriborsci , Grigory Yaremenko , Georgiy Malaniya

We study episodic reinforcement learning in Markov decision processes when the agent receives additional feedback per step in the form of several transition observations. Such additional observations are available in a range of tasks…

机器学习 · 计算机科学 2020-05-11 Christoph Dann , Yishay Mansour , Mehryar Mohri , Ayush Sekhari , Karthik Sridharan

Measuring states in reinforcement learning (RL) can be costly in real-world settings and may negatively influence future outcomes. We introduce the Actively Observable Markov Decision Process (AOMDP), where an agent not only selects control…

机器学习 · 计算机科学 2025-10-17 Daiqi Gao , Ziping Xu , Aseel Rawashdeh , Predrag Klasnja , Susan A. Murphy

We consider un-discounted reinforcement learning (RL) in Markov decision processes (MDPs) under temporal drifts, ie, both the reward and state transition distributions are allowed to evolve over time, as long as their respective total…

机器学习 · 计算机科学 2020-05-19 Wang Chi Cheung , David Simchi-Levi , Ruihao Zhu

Model-based Reinforcement Learning (RL) is a popular learning paradigm due to its potential sample efficiency compared to model-free RL. However, existing empirical model-based RL approaches lack the ability to explore. This work studies a…

机器学习 · 计算机科学 2021-07-16 Yuda Song , Wen Sun

Reinforcement Learning Algorithms are predominantly developed for stationary environments, and the limited literature that considers nonstationary environments often involves specific assumptions about changes that can occur in transition…

机器学习 · 计算机科学 2025-09-25 Ranga Shaarad Ayyagari , Revanth Raj Eega , Ambedkar Dukkipati

A fundamental question in the theory of reinforcement learning is: suppose the optimal $Q$-function lies in the linear span of a given $d$ dimensional feature mapping, is sample-efficient reinforcement learning (RL) possible? The recent and…

机器学习 · 计算机科学 2021-10-22 Yuanhao Wang , Ruosong Wang , Sham M. Kakade

In many practical applications, decision-making processes must balance the costs of acquiring information with the benefits it provides. Traditional control systems often assume full observability, an unrealistic assumption when…

人工智能 · 计算机科学 2025-01-24 Taiyi Wang , Jianheng Liu , Bryan Lee , Zhihao Wu , Yu Wu

The Robust Markov Decision Process (RMDP) framework focuses on designing control policies that are robust against the parameter uncertainties due to the mismatches between the simulator model and real-world settings. An RMDP problem is…

机器学习 · 计算机科学 2022-05-17 Kishan Panaganti , Dileep Kalathil

The agent learns to organize decision behavior to achieve a behavioral goal, such as reward maximization, and reinforcement learning is often used for this optimization. Learning an optimal behavioral strategy is difficult under the…

机器学习 · 计算机科学 2023-05-09 Kazuki Takahashi , Tomoki Fukai , Yutaka Sakai , Takashi Takekawa

Reinforcement learning (RL) methods have been shown to be capable of learning intelligent behavior in rich domains. However, this has largely been done in simulated domains without adequate focus on the process of building the simulator. In…

机器学习 · 计算机科学 2019-10-24 Aditya Modi , Nan Jiang , Ambuj Tewari , Satinder Singh

We consider reinforcement learning in an environment modeled by an episodic, finite, stage-dependent Markov decision process of horizon $H$ with $S$ states, and $A$ actions. The performance of an agent is measured by the regret after…

Data assimilation (DA) has increasingly emerged as a critical tool for state estimation across a wide range of applications. It is significantly challenging when the governing equations of the underlying dynamics are unknown. To this end,…

机器学习 · 计算机科学 2026-01-13 Ziyi Wang , Lijian Jiang

We study offline Reinforcement Learning in large infinite-horizon discounted Markov Decision Processes (MDPs) when the reward and transition models are linearly realizable under a known feature map. Starting from the classic linear-program…

机器学习 · 计算机科学 2024-05-24 Gergely Neu , Nneka Okolo