中文
相关论文

相关论文: Reinforcement Learning with Imperfect Transition P…

200 篇论文

We study reinforcement learning (RL) with linear function approximation in Markov Decision Processes (MDPs) satisfying \emph{linear Bellman completeness} -- a fundamental setting where the Bellman backup of any linear value function remains…

机器学习 · 计算机科学 2026-03-25 Zakaria Mhammedi , Alexander Rakhlin , Nneka Okolo

We study model-based reinforcement learning (RL) for episodic Markov decision processes (MDP) whose transition probability is parametrized by an unknown transition core with features of state and action. Despite much recent progress in…

机器学习 · 统计学 2024-11-19 Taehyun Hwang , Min-hwan Oh

Fairness plays a crucial role in various multi-agent systems (e.g., communication networks, financial markets, etc.). Many multi-agent dynamical interactions can be cast as Markov Decision Processes (MDPs). While existing research has…

机器学习 · 计算机科学 2023-06-02 Peizhong Ju , Arnob Ghosh , Ness B. Shroff

Batch reinforcement learning (RL) is important to apply RL algorithms to many high stakes tasks. Doing batch RL in a way that yields a reliable new policy in large domains is challenging: a new decision policy may visit states and actions…

机器学习 · 计算机科学 2020-07-23 Yao Liu , Adith Swaminathan , Alekh Agarwal , Emma Brunskill

We consider online reinforcement learning (RL) in episodic Markov decision processes (MDPs) under the linear $q^\pi$-realizability assumption, where it is assumed that the action-values of all policies can be expressed as linear functions…

机器学习 · 计算机科学 2023-12-21 Gellért Weisz , András György , Csaba Szepesvári

In this paper we consider the basic version of Reinforcement Learning (RL) that involves computing optimal data driven (adaptive) policies for Markovian decision process with unknown transition probabilities. We provide a brief survey of…

机器学习 · 计算机科学 2019-09-16 Wesley Cowan , Michael N. Katehakis , Daniel Pirutinsky

A promising way to improve the sample efficiency of reinforcement learning is model-based methods, in which many explorations and evaluations can happen in the learned models to save real-world samples. However, when the learned model has a…

机器学习 · 计算机科学 2022-09-14 Haoxin Lin , Yihao Sun , Jiaji Zhang , Yang Yu

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

Reinforcement learning (RL) methods often rely on massive exploration data to search optimal policies, and suffer from poor sampling efficiency. This paper presents a mixed reinforcement learning (mixed RL) algorithm by simultaneously using…

系统与控制 · 电气工程与系统科学 2020-03-03 Yao Mu , Shengbo Eben Li , Chang Liu , Qi Sun , Bingbing Nie , Bo Cheng , Baiyu Peng

Robot learning is often difficult due to the expense of gathering data. The need for large amounts of data can, and should, be tackled with effective algorithms and leveraging expert information on robot dynamics. Bayesian reinforcement…

机器人学 · 计算机科学 2023-07-25 Hai Nguyen , Sammie Katt , Yuchen Xiao , Christopher Amato

Model-based offline reinforcement learning (RL) aims to find highly rewarding policy, by leveraging a previously collected static dataset and a dynamics model. While the dynamics model learned through reuse of the static dataset, its…

机器学习 · 计算机科学 2022-11-01 Kaiyang Guo , Yunfeng Shao , Yanhui Geng

To overcome the curses of dimensionality and modeling of Dynamic Programming (DP) methods to solve Markov Decision Process (MDP) problems, Reinforcement Learning (RL) methods are adopted in practice. Contrary to traditional RL algorithms…

机器学习 · 计算机科学 2021-08-24 Arghyadip Roy , Vivek Borkar , Abhay Karandikar , Prasanna Chaporkar

Reinforcement learning (RL) algorithms assume that users specify tasks by manually writing down a reward function. However, this process can be laborious and demands considerable technical expertise. Can we devise RL algorithms that instead…

机器学习 · 计算机科学 2022-01-03 Benjamin Eysenbach , Sergey Levine , Ruslan Salakhutdinov

Reinforcement learning (RL) has shown significant promise for sequential portfolio optimization tasks, such as stock trading, where the objective is to maximize cumulative returns while minimizing risks using historical data. However,…

机器学习 · 计算机科学 2025-05-20 Haochen Yuan , Minting Pan , Yunbo Wang , Siyu Gao , Philip S. Yu , Xiaokang Yang

We consider a new form of reinforcement learning (RL) that is based on opportunities to directly learn the optimal control policy and a general Markov decision process (MDP) framework devised to support these opportunities. Derivations of…

机器学习 · 计算机科学 2021-04-02 Yingdong Lu , Mark S. Squillante , Chai Wah Wu

We propose a novel framework for risk-sensitive reinforcement learning (RSRL) that incorporates robustness against transition uncertainty. We define two distinct yet coupled risk measures: an inner risk measure addressing state and cost…

风险管理 · 定量金融 2026-01-01 Shanyu Han , Yangbo He , Yang Liu

Online reinforcement learning (RL) has been widely applied in information processing scenarios, which usually exhibit much uncertainty due to the intrinsic randomness of channels and service demands. In this paper, we consider an…

机器学习 · 计算机科学 2021-06-17 Rongpeng Li

Bayesian reinforcement learning (BRL) encodes prior knowledge of the world in a model and represents uncertainty in model parameters by maintaining a probability distribution over them. This paper presents Monte Carlo BRL (MC-BRL), a simple…

机器学习 · 计算机科学 2012-07-03 Yi Wang , Kok Sung Won , David Hsu , Wee Sun Lee

A Markov decision process can be parameterized by a transition kernel and a reward function. Both play essential roles in the study of reinforcement learning as evidenced by their presence in the Bellman equations. In our inquiry of various…

机器学习 · 计算机科学 2023-09-04 Falcon Z. Dai

A popular perspective in Reinforcement learning (RL) casts the problem as probabilistic inference on a graphical model of the Markov decision process (MDP). The core object of study is the probability of each state-action pair being visited…

机器学习 · 计算机科学 2023-11-23 Jean Tarbouriech , Tor Lattimore , Brendan O'Donoghue
‹ 上一页 1 2 3 10 下一页 ›