中文
相关论文

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

200 篇论文

We consider the problem of learning by demonstration from agents acting in unknown stochastic Markov environments or games. Our aim is to estimate agent preferences in order to construct improved policies for the same task that the agents…

机器学习 · 统计学 2013-07-16 Aristide C. Y. Tossou , Christos Dimitrakakis

We study reinforcement learning with delayed state observation, where the agent observes the current state after some random number of time steps. We propose an algorithm that combines the augmentation method and the upper confidence bound…

机器学习 · 计算机科学 2026-03-05 Harin Lee , Kevin Jamieson

In many interactive decision-making settings, there is latent and unobserved information that remains fixed. Consider, for example, a dialogue system, where complete information about a user, such as the user's preferences, is not given. In…

机器学习 · 计算机科学 2023-10-12 Jeongyeol Kwon , Yonathan Efroni , Shie Mannor , Constantine Caramanis

Reinforcement learning (RL) is currently one of the most prominent methods for optimizing dynamical systems, with breakthrough results across various fields. The framework is based on the concept of a Markov decision process (MDP), leading…

最优化与控制 · 数学 2025-11-17 Rene Carmona , Mathieu Lauriere

The theory of reinforcement learning has focused on two fundamental problems: achieving low regret, and identifying $\epsilon$-optimal policies. While a simple reduction allows one to apply a low-regret algorithm to obtain an…

机器学习 · 计算机科学 2022-06-23 Andrew Wagenmaker , Max Simchowitz , Kevin Jamieson

Transformers have demonstrated exceptional performance across a wide range of domains. While their ability to perform reinforcement learning in-context has been established both theoretically and empirically, their behavior in…

机器学习 · 统计学 2025-10-24 Baiyuan Chen , Shinji Ito , Masaaki Imaizumi

We consider the problem of learning-based man-in-the-middle (MITM) attacks in cyber-physical systems (CPS), and extend our previously proposed Bellman Deviation Detection (BDD) framework for model-free reinforcement learning (RL). We refine…

系统与控制 · 电气工程与系统科学 2026-04-02 Rishi Rani , Massimo Franceschetti

Humans achieve efficient learning by relying on prior knowledge about the structure of naturally occurring tasks. There is considerable interest in designing reinforcement learning (RL) algorithms with similar properties. This includes…

机器学习 · 计算机科学 2019-10-23 Jan Humplik , Alexandre Galashov , Leonard Hasenclever , Pedro A. Ortega , Yee Whye Teh , Nicolas Heess

Reinforcement learning (RL) algorithms find applications in inventory control, recommender systems, vehicular traffic management, cloud computing and robotics. The real-world complications of many tasks arising in these domains makes them…

机器学习 · 计算机科学 2021-06-03 Sindhu Padakandla

Meta reinforcement learning (Meta RL) has been amply explored to quickly learn an unseen task by transferring previously learned knowledge from similar tasks. However, most state-of-the-art algorithms require the meta-training tasks to have…

机器学习 · 计算机科学 2023-11-14 Lu Wen , Songan Zhang , H. Eric Tseng , Huei Peng

We develop several provably efficient model-free reinforcement learning (RL) algorithms for infinite-horizon average-reward Markov Decision Processes (MDPs). We consider both online setting and the setting with access to a simulator. In the…

机器学习 · 计算机科学 2023-06-29 Zihan Zhang , Qiaomin Xie

While most approaches to the problem of Inverse Reinforcement Learning (IRL) focus on estimating a reward function that best explains an expert agent's policy or demonstrated behavior on a control task, it is often the case that such…

机器学习 · 计算机科学 2020-05-01 Dexter R. R. Scobee , S. Shankar Sastry

We consider offline reinforcement learning (RL) methods in possibly nonstationary environments. Many existing RL algorithms in the literature rely on the stationarity assumption that requires the system transition and the reward function to…

机器学习 · 统计学 2025-01-07 Mengbing Li , Chengchun Shi , Zhenke Wu , Piotr Fryzlewicz

Robotic systems must be able to quickly and robustly make decisions when operating in uncertain and dynamic environments. While Reinforcement Learning (RL) can be used to compute optimal policies with little prior knowledge about the…

机器人学 · 计算机科学 2016-09-13 Yunpeng Pan , Xinyan Yan , Evangelos Theodorou , Byron Boots

Given a Markov decision process (MDP), we seek to learn representations for a range of policies to facilitate behavior steering at test time. As policies of an MDP are uniquely determined by their occupancy measures, we propose modeling…

机器学习 · 计算机科学 2026-02-02 Beiming Li , Sergio Rozada , Alejandro Ribeiro

Delayed Markov decision processes (DMDPs) fulfill the Markov property by augmenting the state space of agents with a finite time window of recently committed actions. In reliance on these state augmentations, delay-resolved reinforcement…

机器人学 · 计算机科学 2025-11-17 Mohammadhossein Malmir , Josip Josifovski , Noah Klarmann , Alois Knoll

Meta-gradient methods (Xu et al., 2018; Zahavy et al., 2020) offer a promising solution to the problem of hyperparameter selection and adaptation in non-stationary reinforcement learning problems. However, the properties of meta-gradients…

机器学习 · 计算机科学 2022-09-14 Jelena Luketina , Sebastian Flennerhag , Yannick Schroecker , David Abel , Tom Zahavy , Satinder Singh

This paper addresses the problem of learning control policies for mobile robots, modeled as unknown Markov Decision Processes (MDPs), that are tasked with temporal logic missions, such as sequencing, coverage, or surveillance. The MDP…

机器人学 · 计算机科学 2022-07-13 Yiannis Kantaros

Hybrid Reinforcement Learning (RL), where an agent learns from both an offline dataset and online explorations in an unknown environment, has garnered significant recent interest. A crucial question posed by Xie et al. (2022) is whether…

机器学习 · 统计学 2024-08-09 Kevin Tan , Wei Fan , Yuting Wei

We consider offline Reinforcement Learning (RL), where the agent does not interact with the environment and must rely on offline data collected using a behavior policy. Previous works provide policy evaluation guarantees when the target…

机器学习 · 计算机科学 2023-05-26 Xumei Xi , Christina Lee Yu , Yudong Chen