中文
相关论文

相关论文: Reinforcement Learning of Markov Decision Processe…

200 篇论文

To ensure the usefulness of Reinforcement Learning (RL) in real systems, it is crucial to ensure they are robust to noise and adversarial attacks. In adversarial RL, an external attacker has the power to manipulate the victim agent's…

机器学习 · 计算机科学 2024-06-18 Jeremy McMahan , Young Wu , Xiaojin Zhu , Qiaomin Xie

In this paper, we study the learning of safe policies in the setting of reinforcement learning problems. This is, we aim to control a Markov Decision Process (MDP) of which we do not know the transition probabilities, but we have access to…

系统与控制 · 电气工程与系统科学 2022-01-14 Santiago Paternain , Miguel Calvo-Fullana , Luiz F. O. Chamon , Alejandro Ribeiro

We study policy gradient methods for reinforcement learning in non-Markovian decision processes (NMDPs), where observations and rewards depend on the entire interaction history. To handle this dependence, the agent maintains an internal…

Markov Decision Processes (MDPs) have been used to formulate many decision-making problems in science and engineering. The objective is to synthesize the best decision (action selection) policies to maximize expected rewards (minimize…

最优化与控制 · 数学 2015-07-08 Mahmoud El Chamie , Behcet Acikmese

In typical reinforcement learning (RL), the environment is assumed given and the goal of the learning is to identify an optimal policy for the agent taking actions through its interactions with the environment. In this paper, we extend this…

人工智能 · 计算机科学 2019-10-25 Haifeng Zhang , Jun Wang , Zhiming Zhou , Weinan Zhang , Ying Wen , Yong Yu , Wenxin Li

We consider the task of Inverse Reinforcement Learning in Contextual Markov Decision Processes (MDPs). In this setting, contexts, which define the reward and transition kernel, are sampled from a distribution. In addition, although the…

机器学习 · 计算机科学 2021-01-01 Stav Belogolovsky , Philip Korsunsky , Shie Mannor , Chen Tessler , Tom Zahavy

We present the problem of reinforcement learning with exogenous termination. We define the Termination Markov Decision Process (TerMDP), an extension of the MDP framework, in which episodes may be interrupted by an external non-Markovian…

机器学习 · 计算机科学 2023-10-09 Guy Tennenholtz , Nadav Merlis , Lior Shani , Shie Mannor , Uri Shalit , Gal Chechik , Assaf Hallak , Gal Dalal

We propose a general framework for entropy-regularized average-reward reinforcement learning in Markov decision processes (MDPs). Our approach is based on extending the linear-programming formulation of policy optimization in MDPs to…

机器学习 · 计算机科学 2017-05-23 Gergely Neu , Anders Jonsson , Vicenç Gómez

Reactive synthesis algorithms allow automatic construction of policies to control an environment modeled as a Markov Decision Process (MDP) that are optimal with respect to high-level temporal logic specifications. However, they assume that…

形式语言与自动机理论 · 计算机科学 2022-05-31 Rajeev Alur , Suguman Bansal , Osbert Bastani , Kishor Jothimurugan

In several reinforcement learning (RL) scenarios, mainly in security settings, there may be adversaries trying to interfere with the reward generating process. In this paper, we introduce Threatened Markov Decision Processes (TMDPs), which…

机器学习 · 计算机科学 2019-10-28 Victor Gallego , Roi Naveiro , David Rios Insua

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

General-purpose, intelligent, learning agents cycle through sequences of observations, actions, and rewards that are complex, uncertain, unknown, and non-Markovian. On the other hand, reinforcement learning is well-developed for small…

机器学习 · 计算机科学 2009-12-30 Marcus Hutter

We study reinforcement learning with linear function approximation and finite-memory approximations for partially observed Markov decision processes (POMDPs). We first present an algorithm for the value evaluation of finite-memory feedback…

最优化与控制 · 数学 2025-05-22 Ali Devran Kara

This paper proposes a reinforcement learning method for controller synthesis of autonomous systems in unknown and partially-observable environments with subjective time-dependent safety constraints. Mathematically, we model the system…

机器人学 · 计算机科学 2021-04-06 Yu Wang , Alper Kamil Bozkurt , Miroslav Pajic

We study the problem of synthesizing a policy that maximizes the entropy of a Markov decision process (MDP) subject to a temporal logic constraint. Such a policy minimizes the predictability of the paths it generates, or dually, maximizes…

最优化与控制 · 数学 2019-06-17 Yagiz Savas , Melkior Ornik , Murat Cubuktepe , Mustafa O. Karabag , Ufuk Topcu

A Markov Decision Process (MDP) is a popular model for reinforcement learning. However, its commonly used assumption of stationary dynamics and rewards is too stringent and fails to hold in adversarial, nonstationary, or multi-agent…

机器学习 · 计算机科学 2019-08-22 Tiancheng Yu , Suvrit Sra

This paper proposes a multi-agent reinforcement learning based medium access framework for wireless networks. The access problem is formulated as a Markov Decision Process (MDP), and solved using reinforcement learning with every network…

机器学习 · 计算机科学 2021-04-30 Hrishikesh Dutta , Subir Biswas

Inverse reinforcement learning is the problem of inferring a reward function from an optimal policy or demonstrations by an expert. In this work, it is assumed that the reward is expressed as a reward machine whose transitions depend on…

机器学习 · 计算机科学 2025-10-23 Mohamad Louai Shehab , Antoine Aspeel , Necmiye Ozay

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

We present a method for a certain class of Markov Decision Processes (MDPs) that can relate the optimal policy back to one or more reward sources in the environment. For a given initial state, without fully computing the value function,…

机器学习 · 计算机科学 2018-06-12 Josh Bertram , Peng Wei