中文
相关论文

相关论文: Symmetric Q-learning: Reducing Skewness of Bellman…

200 篇论文

We consider the question of learning $Q$-function in a sample efficient manner for reinforcement learning with continuous state and action spaces under a generative model. If $Q$-function is Lipschitz continuous, then the minimal sample…

机器学习 · 计算机科学 2020-06-12 Devavrat Shah , Dogyoon Song , Zhi Xu , Yuzhe Yang

Although distributional reinforcement learning (DRL) has been widely examined in the past few years, very few studies investigate the validity of the obtained Q-function estimator in the distributional setting. To fully understand how the…

机器学习 · 计算机科学 2023-08-01 Qi Kuang , Zhoufan Zhu , Liwen Zhang , Fan Zhou

Reinforcement learning (RL) has seen significant research and application results but often requires large amounts of training data. This paper proposes two data-efficient off-policy RL methods that use parametrized Q-learning. In these…

系统与控制 · 电气工程与系统科学 2025-04-09 J. S. van Hulst , W. P. M. H. Heemels , D. J. Antunes

This paper addresses the average cost minimization problem for discrete-time systems with multiplicative and additive noises via reinforcement learning. By using Q-function, we propose an online learning scheme to estimate the kernel matrix…

系统与控制 · 电气工程与系统科学 2020-10-14 Jing Lai , Junlin Xiong

This paper develops an inverse reinforcement learning algorithm aimed at recovering a reward function from the observed actions of an agent. We introduce a strategy to flexibly handle different types of actions with two approximations of…

机器学习 · 计算机科学 2017-07-26 Kun Li , Yanan Sui , Joel W. Burdick

Reinforcement learning (RL) has emerged as a key approach for training agents in complex and uncertain environments. Incorporating statistical inference in RL algorithms is essential for understanding and managing uncertainty in model…

机器学习 · 计算机科学 2025-02-28 Saunak Kumar Panda , Ruiqi Liu , Yisha Xiang

In real scenarios, state observations that an agent observes may contain measurement errors or adversarial noises, misleading the agent to take suboptimal actions or even collapse while training. In this paper, we study the training…

机器学习 · 计算机科学 2023-06-23 Ke Sun , Yingnan Zhao , Shangling Jui , Linglong Kong

The use of target networks in deep reinforcement learning is a widely popular solution to mitigate the brittleness of semi-gradient approaches and stabilize learning. However, target networks notoriously require additional memory and delay…

机器学习 · 计算机科学 2026-03-02 Théo Vincent , Yogesh Tripathi , Tim Faust , Abdullah Akgül , Yaniv Oren , Melih Kandemir , Jan Peters , Carlo D'Eramo

$Q$-learning is one of the most fundamental reinforcement learning algorithms. It is widely believed that $Q$-learning with linear function approximation (i.e., linear $Q$-learning) suffers from possible divergence until the recent work…

机器学习 · 计算机科学 2025-05-28 Xinyu Liu , Zixuan Xie , Shangtong Zhang

In classical Q-learning, the objective is to maximize the sum of discounted rewards through iteratively using the Bellman equation as an update, in an attempt to estimate the action value function of the optimal policy. Conventionally, the…

机器学习 · 计算机科学 2019-06-25 Hadi S. Jomaa , Josif Grabocka , Lars Schmidt-Thieme

Reinforcement learning algorithms can solve dynamic decision-making and optimal control problems. With continuous-valued state and input variables, reinforcement learning algorithms must rely on function approximators to represent the value…

机器学习 · 计算机科学 2021-11-16 Jiří Kubalík , Erik Derner , Jan Žegklitz , Robert Babuška

Most value function learning algorithms in reinforcement learning are based on the mean squared (projected) Bellman error. However, squared errors are known to be sensitive to outliers, both skewing the solution of the objective and…

机器学习 · 计算机科学 2023-04-19 Andrew Patterson , Victor Liao , Martha White

This paper considers a stochastic linear quadratic problem for discrete-time systems with multiplicative noises over an infinite horizon. To obtain the optimal solution, we propose an online iterative algorithm of reinforcement learning…

最优化与控制 · 数学 2023-11-22 Hongdan Li , Lucky Qiaofeng Li , Xun Li , Zhaorong Zhang

Reinforcement learning (RL) with limited samples is common in real-world applications. However, offline RL performance under this constraint is often suboptimal. We consider an alternative approach to dealing with limited samples by…

机器学习 · 计算机科学 2025-11-14 Outongyi Lv , Yewei Yuan , Nana Liu

We prove performance guarantees of two algorithms for approximating $Q^\star$ in batch reinforcement learning. Compared to classical iterative methods such as Fitted Q-Iteration---whose performance loss incurs quadratic dependence on…

机器学习 · 计算机科学 2020-08-25 Tengyang Xie , Nan Jiang

Q-learning is a fundamental algorithmic primitive in reinforcement learning. This paper develops a new framework for analyzing Q-learning from a switching-system viewpoint. In particular, we derive a direct stochastic switching-system…

机器学习 · 计算机科学 2026-05-06 Donghwan Lee

We study computationally and statistically efficient Reinforcement Learning algorithms for the linear Bellman Complete setting. This setting uses linear function approximation to capture value functions and unifies existing models like…

机器学习 · 计算机科学 2025-03-04 Runzhe Wu , Ayush Sekhari , Akshay Krishnamurthy , Wen Sun

Scaling reinforcement learning (RL) to recommender systems (RS) is promising since maximizing the expected cumulative rewards for RL agents meets the objective of RS, i.e., improving customers' long-term satisfaction. A key approach to this…

机器学习 · 计算机科学 2022-09-27 Chengqian Gao , Ke Xu , Kuangqi Zhou , Lanqing Li , Xueqian Wang , Bo Yuan , Peilin Zhao

In value-based deep reinforcement learning methods, approximation of value functions induces overestimation bias and leads to suboptimal policies. We show that in deep actor-critic methods that aim to overcome the overestimation bias, if…

机器学习 · 计算机科学 2021-12-28 Baturay Saglam , Enes Duran , Dogan C. Cicek , Furkan B. Mutlu , Suleyman S. Kozat

We propose a new reinforcement learning (RL) formulation for training continuous-time score-based diffusion models for generative AI to generate samples that maximize reward functions while keeping the generated distributions close to the…

机器学习 · 计算机科学 2025-08-12 Xuefeng Gao , Jiale Zha , Xun Yu Zhou