English
Related papers

Related papers: Smoothed Q-learning

200 papers

In this work, we present a new model-free and off-policy reinforcement learning (RL) algorithm, that is capable of finding a near-optimal policy with state-action observations from arbitrary behavior policies. Our algorithm, called the…

Optimization and Control · Mathematics 2025-07-21 Narim Jeong , Donghwan Lee , Niao He

Artificial neural networks are promising for general function approximation but challenging to train on non-independent or non-identically distributed data due to catastrophic forgetting. The experience replay buffer, a standard component…

Machine Learning · Computer Science 2023-04-12 Qingfeng Lan , Yangchen Pan , Jun Luo , A. Rupam Mahmood

Clinical decision-making often involves selecting tests that are costly, invasive, or time-consuming, motivating individualized, sequential strategies for what to measure and when to stop ascertaining. We study the problem of learning…

Machine Learning · Statistics 2026-04-16 Doudou Zhou , Yiran Zhang , Dian Jin , Yingye Zheng , Lu Tian , Tianxi Cai

In this paper, we establish a theoretical comparison between the asymptotic mean-squared error of Double Q-learning and Q-learning. Our result builds upon an analysis for linear stochastic approximation based on Lyapunov equations and…

Machine Learning · Computer Science 2022-06-16 Wentao Weng , Harsh Gupta , Niao He , Lei Ying , R. Srikant

Q-learning is a popular Reinforcement Learning (RL) algorithm which is widely used in practice with function approximation (Mnih et al., 2015). In contrast, existing theoretical results are pessimistic about Q-learning. For example, (Baird,…

Machine Learning · Computer Science 2021-10-20 Naman Agarwal , Syomantak Chaudhuri , Prateek Jain , Dheeraj Nagaraj , Praneeth Netrapalli

The exploration-exploitation dilemma has been a central challenge in reinforcement learning (RL) with complex model classes. In this paper, we propose a new algorithm, Monotonic Q-Learning with Upper Confidence Bound (MQL-UCB) for RL with…

Machine Learning · Computer Science 2025-10-06 Heyang Zhao , Jiafan He , Quanquan Gu

The primary goal of reinforcement learning is to develop decision-making policies that prioritize optimal performance without considering risk or safety. In contrast, safe reinforcement learning aims to mitigate or avoid unsafe states. This…

Machine Learning · Computer Science 2024-09-13 Zahra Shahrooei , Ali Baheri

The core challenge of offline reinforcement learning (RL) is dealing with the (potentially catastrophic) extrapolation error induced by the distribution shift between the history dataset and the desired policy. A large portion of prior work…

Machine Learning · Computer Science 2023-07-27 Laixi Shi , Robert Dadashi , Yuejie Chi , Pablo Samuel Castro , Matthieu Geist

Hierarchical Reinforcement Learning promises, among other benefits, to efficiently capture and utilize the temporal structure of a decision-making problem and to enhance continual learning capabilities, but theoretical guarantees lag behind…

Machine Learning · Computer Science 2025-11-24 Massimiliano Manenti , Andrea Iannelli

The study of unsupervised learning can be generally divided into two categories: imitation learning and reinforcement learning. In imitation learning the machine learns by mimicking the behavior of an expert system whereas in reinforcement…

Machine Learning · Computer Science 2020-04-07 Xiao Lei Zhang , Anish Agarwal

Effectively leveraging large, previously collected datasets in reinforcement learning (RL) is a key challenge for large-scale real-world applications. Offline RL algorithms promise to learn effective policies from previously-collected,…

Machine Learning · Computer Science 2020-08-20 Aviral Kumar , Aurick Zhou , George Tucker , Sergey Levine

Q-learning can be described as an all-purpose automaton that provides estimates (Q-values) of the continuation values associated with each available action and follows the naive policy of almost always choosing the action with highest…

Theoretical Economics · Economics 2025-05-29 Olivier Compte

Bimodal, stochastic environments present a challenge to typical Reinforcement Learning problems. This problem is one that is surprisingly common in real world applications, being particularly applicable to pricing problems. In this paper we…

Machine Learning · Computer Science 2023-07-04 E. Hurwitz , N. Peace , G. Cevora

Q-learning and SARSA are foundational reinforcement learning algorithms whose practical success depends critically on step-size calibration. Step-sizes that are too large can cause numerical instability, while step-sizes that are too small…

Machine Learning · Statistics 2026-01-28 Hwanwoo Kim , Eric Laber

Can simple algorithms with a good representation solve challenging reinforcement learning problems? In this work, we answer this question in the affirmative, where we take "simple learning algorithm" to be tabular Q-Learning, the "good…

Machine Learning · Computer Science 2020-02-14 Kavosh Asadi , David Abel , Michael L. Littman

Reinforcement learning has been widely used in many problems, including quantum control of qubits. However, such problems can, at the same time, be solved by traditional, non-machine-learning methods, such as stochastic gradient descent and…

Quantum Physics · Physics 2021-05-06 Xiao-Ming Zhang , Zezhu Wei , Raza Asad , Xu-Chen Yang , Xin Wang

Reinforcement learning (RL) is a control approach that can handle nonlinear stochastic optimal control problems. However, despite the promise exhibited, RL has yet to see marked translation to industrial practice primarily due to its…

Machine Learning · Computer Science 2021-04-15 Elton Pan , Panagiotis Petsagkourakis , Max Mowbray , Dongda Zhang , Antonio del Rio-Chanona

Deep Q-Learning is an important reinforcement learning algorithm, which involves training a deep neural network, called Deep Q-Network (DQN), to approximate the well-known Q-function. Although wildly successful under laboratory conditions,…

Machine Learning · Computer Science 2021-04-13 Arunselvan Ramaswamy , Eyke Hüllermeier

Q-learning excels in learning from feedback within sequential decision-making tasks but often requires extensive sampling to achieve significant improvements. While reward shaping can enhance learning efficiency, non-potential-based methods…

Machine Learning · Computer Science 2024-05-27 Xiefeng Wu

Learning complicated value functions in high dimensional state space by function approximation is a challenging task, partially due to that the max-operator used in temporal difference updates can theoretically cause instability for most…

Machine Learning · Computer Science 2020-12-21 Yaozhong Gan , Zhe Zhang , Xiaoyang Tan