中文
相关论文

相关论文: Minimum-Delay Adaptation in Non-Stationary Reinfor…

200 篇论文

The Markov decision process (MDP) formulation used to model many real-world sequential decision making problems does not efficiently capture the setting where the set of available decisions (actions) at each time step is stochastic.…

机器学习 · 计算机科学 2020-01-22 Yash Chandak , Georgios Theocharous , Blossom Metevier , Philip S. Thomas

Safe Reinforcement Learning (RL) plays an important role in applying RL algorithms to safety-critical real-world applications, addressing the trade-off between maximizing rewards and adhering to safety constraints. This work introduces a…

机器人学 · 计算机科学 2024-07-16 Fan Yang , Wenxuan Zhou , Zuxin Liu , Ding Zhao , David Held

This article provides a rigorous analysis of convergence and stability of Episodic Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning and Online Decision Transformers. These algorithms performed competitively across…

The key challenge in multiagent learning is learning a best response to the behaviour of other agents, which may be non-stationary: if the other agents adapt their strategy as well, the learning target moves. Disparate streams of research…

多智能体系统 · 计算机科学 2019-03-13 Pablo Hernandez-Leal , Michael Kaisers , Tim Baarslag , Enrique Munoz de Cote

Safe reinforcement learning has been a promising approach for optimizing the policy of an agent that operates in safety-critical applications. In this paper, we propose an algorithm, SNO-MDP, that explores and optimizes Markov decision…

机器学习 · 计算机科学 2020-08-18 Akifumi Wachi , Yanan Sui

This paper addresses the challenge of offline policy learning in reinforcement learning with continuous action spaces when unmeasured confounders are present. While most existing research focuses on policy evaluation within partially…

机器学习 · 统计学 2025-05-02 Yuhan Li , Eugene Han , Yifan Hu , Wenzhuo Zhou , Zhengling Qi , Yifan Cui , Ruoqing Zhu

Social goods, such as healthcare, smart city, and information networks, often produce ordered event data in continuous time. The generative processes of these event data can be very complex, requiring flexible models to capture their…

机器学习 · 计算机科学 2020-12-29 Shuang Li , Shuai Xiao , Shixiang Zhu , Nan Du , Yao Xie , Le Song

Reinforcement learning considers the problem of finding policies that maximize an expected cumulative reward in a Markov decision process with unknown transition probabilities. In this paper we consider the problem of finding optimal…

机器学习 · 计算机科学 2020-10-19 Santiago Paternain , Juan Andres Bazerque , Alejandro Ribeiro

In probably approximately correct (PAC) reinforcement learning (RL), an agent is required to identify an $\epsilon$-optimal policy with probability $1-\delta$. While minimax optimal algorithms exist for this problem, its instance-dependent…

机器学习 · 计算机科学 2022-10-25 Andrea Tirinzoni , Aymen Al-Marjani , Emilie Kaufmann

We study online learning in constrained Markov decision processes (CMDPs) with adversarial losses and stochastic hard constraints, under bandit feedback. We consider three scenarios. In the first one, we address general CMDPs, where we…

机器学习 · 计算机科学 2025-02-10 Francesco Emanuele Stradi , Matteo Castiglioni , Alberto Marchesi , Nicola Gatti

We study the offline data-driven sequential decision making problem in the framework of Markov decision process (MDP). In order to enhance the generalizability and adaptivity of the learned policy, we propose to evaluate each policy by a…

统计理论 · 数学 2021-11-11 Zhengling Qi , Peng Liao

Many control tasks exhibit similar dynamics that can be modeled as having common latent structure. Hidden-Parameter Markov Decision Processes (HiP-MDPs) explicitly model this structure to improve sample efficiency in multi-task settings.…

机器学习 · 计算机科学 2021-02-15 Amy Zhang , Shagun Sodhani , Khimya Khetarpal , Joelle Pineau

Robust reinforcement learning is essential for deploying reinforcement learning algorithms in real-world scenarios where environmental uncertainty predominates. Traditional robust reinforcement learning often depends on rectangularity…

机器学习 · 计算机科学 2024-06-13 Adil Zouitine , David Bertoin , Pierre Clavier , Matthieu Geist , Emmanuel Rachelson

Dynamic mechanism design studies how mechanism designers should allocate resources among agents in a time-varying environment. We consider the problem where the agents interact with the mechanism designer according to an unknown Markov…

机器学习 · 计算机科学 2024-12-19 Shuang Qiu , Boxiang Lyu , Qinglin Meng , Zhaoran Wang , Zhuoran Yang , Michael I. Jordan

We introduce data-driven decision-making algorithms that achieve state-of-the-art \emph{dynamic regret} bounds for non-stationary bandit settings. These settings capture applications such as advertisement allocation, dynamic pricing, and…

机器学习 · 计算机科学 2021-03-19 Wang Chi Cheung , David Simchi-Levi , Ruihao Zhu

Deep Reinforcement Learning has shown its ability in solving complicated problems directly from high-dimensional observations. However, in end-to-end settings, Reinforcement Learning algorithms are not sample-efficient and requires long…

机器学习 · 计算机科学 2021-07-06 Nicolò Botteghi , Mannes Poel , Beril Sirmacek , Christoph Brune

In a typical stochastic multi-armed bandit problem, the objective is often to maximize the expected sum of rewards over some time horizon $T$. While the choice of a strategy that accomplishes that is optimal with no additional information,…

机器学习 · 计算机科学 2023-11-01 Reda Alami , Mohammed Mahfoud , Mastane Achab

We study lifelong reinforcement learning (RL) in a regret minimization setting of linear contextual Markov decision process (MDP), where the agent needs to learn a multi-task policy while solving a streaming sequence of tasks. We propose an…

机器学习 · 计算机科学 2022-06-02 Sanae Amani , Lin F. Yang , Ching-An Cheng

There have been many recent advances on provably efficient Reinforcement Learning (RL) in problems with rich observation spaces. However, all these works share a strong realizability assumption about the optimal value function of the true…

机器学习 · 计算机科学 2021-06-23 Christoph Dann , Yishay Mansour , Mehryar Mohri , Ayush Sekhari , Karthik Sridharan

We consider a high-dimensional dynamic pricing problem under non-stationarity, where a firm sells products to $T$ sequentially arriving consumers that behave according to an unknown demand model with potential changes at unknown times. The…

统计方法学 · 统计学 2023-03-21 Zifeng Zhao , Feiyu Jiang , Yi Yu , Xi Chen