中文
相关论文

相关论文: Online Reinforcement Learning for Real-Time Explor…

200 篇论文

This paper employs a policy iteration reinforcement learning (RL) method to study continuous-time linear-quadratic mean-field control problems in infinite horizon. The drift and diffusion terms in the dynamics involve the states, the…

最优化与控制 · 数学 2024-11-05 Na Li , Xun Li , Zuo Quan Xu

Reinforcement learning (RL) can be used to learn treatment policies and aid decision making in healthcare. However, given the need for generalization over complex state/action spaces, the incorporation of function approximators (e.g., deep…

机器学习 · 计算机科学 2021-07-26 Shengpu Tang , Jenna Wiens

A convenient approach to optimally solving combinatorial optimization tasks is the Branch-and-Bound method. Its branching heuristic can be learned to solve a large set of similar tasks. The promising results here are achieved by the…

机器学习 · 计算机科学 2026-05-22 D. Sorokin , A. Kostin , L. Savchenko , G. Gusev , A. V. Savchenko

Conventional reinforcement learning (RL) methods can successfully solve a wide range of sequential decision problems. However, learning policies that can generalize predictably across multiple tasks in a setting with non-Markovian reward…

机器学习 · 计算机科学 2024-06-04 Guillermo Infante , David Kuric , Anders Jonsson , Vicenç Gómez , Herke van Hoof

Most reinforcement learning (RL) algorithms assume online access to the environment, in which one may readily interleave updates to the policy with experience collection using that policy. However, in many real-world applications such as…

机器学习 · 计算机科学 2020-06-24 Tatsuya Matsushima , Hiroki Furuta , Yutaka Matsuo , Ofir Nachum , Shixiang Gu

Offline reinforcement learning (RL) aims to learn optimal policies from offline datasets, where the parameterization of policies is crucial but often overlooked. Recently, Diffsuion-QL significantly boosts the performance of offline RL by…

机器学习 · 计算机科学 2023-10-27 Bingyi Kang , Xiao Ma , Chao Du , Tianyu Pang , Shuicheng Yan

High-speed online trajectory planning for UAVs poses a significant challenge due to the need for precise modeling of complex dynamics while also being constrained by computational limitations. This paper presents a multi-fidelity…

机器人学 · 计算机科学 2025-08-08 Gilhyun Ryou , Geoffrey Wang , Sertac Karaman

This paper studies the continuous-time reinforcement learning (RL) for optimal switching problems across multiple regimes. We consider a type of exploratory formulation under entropy regularization where the agent randomizes both the timing…

最优化与控制 · 数学 2025-12-23 Yijie Huang , Mengge Li , Xiang Yu , Zhou Zhou

Interest in reinforcement learning (RL) for large-scale systems, comprising extensive populations of intelligent agents interacting with heterogeneous environments, has surged significantly across diverse scientific domains in recent years.…

系统与控制 · 电气工程与系统科学 2025-09-16 Wei Zhang , Jr-Shin Li

Reinforcement Learning (RL) has the promise of providing data-driven support for decision-making in a wide range of problems in healthcare, education, business, and other domains. Classical RL methods focus on the mean of the total return…

机器学习 · 计算机科学 2022-02-02 Elynn Y. Chen , Rui Song , Michael I. Jordan

Model-free or learning-based control, in particular, reinforcement learning (RL), is expected to be applied for complex robotic tasks. Traditional RL requires a policy to be optimized is state-dependent, that means, the policy is a kind of…

机器学习 · 计算机科学 2022-08-09 Taisuke Kobayashi , Kenta Yoshizawa

Policy gradient (PG) is a reinforcement learning (RL) approach that optimizes a parameterized policy model for an expected return using gradient ascent. While PG can work well even in non-Markovian environments, it may encounter plateaus or…

机器学习 · 计算机科学 2024-07-08 Tetsuro Morimura , Kazuhiro Ota , Kenshi Abe , Peinan Zhang

One of the fundamental challenges for offline reinforcement learning (RL) is ensuring robustness to data distribution. Whether the data originates from a near-optimal policy or not, we anticipate that an algorithm should demonstrate its…

机器学习 · 计算机科学 2023-10-18 Xiaohan Hu , Yi Ma , Chenjun Xiao , Yan Zheng , Jianye Hao

Motivated by real-world settings where data collection and policy deployment -- whether for a single agent or across multiple agents -- are costly, we study the problem of on-policy single-agent reinforcement learning (RL) and federated RL…

机器学习 · 统计学 2026-03-11 Haochen Zhang , Zhong Zheng , Lingzhou Xue

We propose a multi-time-scale predictive representation learning method to efficiently learn robust driving policies in an offline manner that generalize well to novel road geometries, and damaged and distracting lane conditions which are…

机器人学 · 计算机科学 2021-03-16 Daniel Graves , Nhat M. Nguyen , Kimia Hassanzadeh , Jun Jin , Jun Luo

In this paper we consider the problem of how a reinforcement learning agent tasked with solving a set of related Markov decision processes can use knowledge acquired early in its lifetime to improve its ability to more rapidly solve novel,…

人工智能 · 计算机科学 2019-02-26 Francisco M. Garcia , Bruno C. da Silva , Philip S. Thomas

Multi-objective reinforcement learning (MORL) is an extension of ordinary, single-objective reinforcement learning (RL) that is applicable to many real-world tasks where multiple objectives exist without known relative costs. We study the…

机器学习 · 计算机科学 2021-01-12 Dongruo Zhou , Jiahao Chen , Quanquan Gu

Reinforcement learning is a general technique that allows an agent to learn an optimal policy and interact with an environment in sequential decision making problems. The goodness of a policy is measured by its value function starting from…

机器学习 · 统计学 2025-06-30 C. Shi , S. Zhang , W. Lu , R. Song

Inspired by recent successes of Monte-Carlo tree search (MCTS) in a number of artificial intelligence (AI) application domains, we propose a model-based reinforcement learning (RL) technique that iteratively applies MCTS on batches of…

人工智能 · 计算机科学 2018-05-16 Daniel R. Jiang , Emmanuel Ekwedike , Han Liu

$Q$-learning is the most fundamental model-free reinforcement learning algorithm. Deployment of $Q$-learning requires approximation of the state-action value function (also known as the $Q$-function). In this work, we provide online random…

机器学习 · 统计学 2022-04-11 Joosung Min , Lloyd T. Elliott