English
Related papers

Related papers: The Mean-Squared Error of Double Q-Learning

200 papers

Semisupervised learning has emerged as a popular framework for improving modeling accuracy while controlling labeling cost. Based on an extension of stochastic composite likelihood we quantify the asymptotic accuracy of generative…

Machine Learning · Computer Science 2010-03-02 Joshua V Dillon , Krishnakumar Balasubramanian , Guy Lebanon

Q-learning, which seeks to learn the optimal Q-function of a Markov decision process (MDP) in a model-free fashion, lies at the heart of reinforcement learning. When it comes to the synchronous setting (such that independent samples for all…

Machine Learning · Statistics 2025-03-18 Gen Li , Changxiao Cai , Yuxin Chen , Yuting Wei , Yuejie Chi

We study the so-called two-time-scale stochastic approximation, a simulation-based approach for finding the roots of two coupled nonlinear operators. Our focus is to characterize its finite-time performance in a Markov setting, which often…

Optimization and Control · Mathematics 2021-04-06 Thinh T. Doan

Double Q-learning is a popular reinforcement learning algorithm in Markov decision process (MDP) problems. Clipped Double Q-learning, as an effective variant of Double Q-learning, employs the clipped double estimator to approximate the…

Machine Learning · Computer Science 2021-05-04 Haobo Jiang , Jin Xie , Jian Yang

We study Q-learning with Polyak-Ruppert averaging in a discounted Markov decision process in synchronous and tabular settings. Under a Lipschitz condition, we establish a functional central limit theorem for the averaged iteration…

Machine Learning · Statistics 2023-02-21 Xiang Li , Wenhao Yang , Jiadong Liang , Zhihua Zhang , Michael I. Jordan

This paper develops an unified framework to study finite-sample convergence guarantees of a large class of value-based asynchronous reinforcement learning (RL) algorithms. We do this by first reformulating the RL algorithms as…

Machine Learning · Computer Science 2023-09-06 Zaiwei Chen , Siva Theja Maguluri , Sanjay Shakkottai , Karthikeyan Shanmugam

In this work, we propose a novel cross Q-learning algorithm, aim at alleviating the well-known overestimation problem in value-based reinforcement learning methods, particularly in the deep Q-networks where the overestimation is exaggerated…

Artificial Intelligence · Computer Science 2020-09-30 Xing Wang , Alexander Vinel

Watkins' and Dayan's Q-learning is a model-free reinforcement learning algorithm that iteratively refines an estimate for the optimal action-value function of an MDP by stochastically "visiting" many state-ation pairs [Watkins and Dayan,…

Machine Learning · Computer Science 2021-08-09 Matthew T. Regehr , Alex Ayoub

We analyze the convergence properties of the two-timescale fictitious play combining the classical fictitious play with the Q-learning for two-player zero-sum stochastic games with player-dependent learning rates. We show its almost sure…

Optimization and Control · Mathematics 2022-04-05 Muhammed O. Sayin , K. Alperen Cetiner

We study the problem of learning an unknown function using random feature models. Our main contribution is an exact asymptotic analysis of such learning problems with Gaussian data. Under mild regularity conditions for the feature matrix,…

Information Theory · Computer Science 2020-08-28 Oussama Dhifallah , Yue M. Lu

This paper studies the q-learning, recently coined as the continuous time counterpart of Q-learning by Jia and Zhou (2023), for continuous time Mckean-Vlasov control problems in the setting of entropy-regularized reinforcement learning. In…

Machine Learning · Computer Science 2024-11-04 Xiaoli Wei , Xiang Yu

Many learning machines such as normal mixtures and layered neural networks are not regular but singular statistical models, because the map from a parameter to a probability distribution is not one-to-one. The conventional statistical…

Statistics Theory · Mathematics 2015-06-03 Koshi Yamada , Sumio Watanabe

Delusional bias is a fundamental source of error in approximate Q-learning. To date, the only techniques that explicitly address delusion require comprehensive search using tabular value estimates. In this paper, we develop efficient…

Machine Learning · Computer Science 2020-03-02 Andy Su , Jayden Ooi , Tyler Lu , Dale Schuurmans , Craig Boutilier

This paper considers the linear-quadratic dual control problem where the system parameters need to be identified and the control objective needs to be optimized in the meantime. Contrary to existing works on data-driven linear-quadratic…

Systems and Control · Electrical Eng. & Systems 2021-11-22 Yiwen Lu , Yilin Mo

Catastrophic forgetting is a critical challenge in training deep neural networks. Although continual learning has been investigated as a countermeasure to the problem, it often suffers from the requirements of additional network components…

Machine Learning · Computer Science 2019-10-23 Dongmin Park , Seokil Hong , Bohyung Han , Kyoung Mu Lee

Despite the sustained popularity of Q-learning as a practical tool for policy determination, a majority of relevant theoretical literature deals with either constant ($\eta_{t}\equiv \eta$) or polynomially decaying ($\eta_{t} = \eta…

Machine Learning · Statistics 2026-04-07 Soham Bonnerjee , Zhipeng Lou , Wei Biao Wu

Double Q-learning is a popular reinforcement learning algorithm in Markov decision process (MDP) problems. Clipped Double Q-learning, as an effective variant of Double Q-learning, employs the clipped double estimator to approximate the…

Machine Learning · Computer Science 2022-03-23 Haobo Jiang , Jin Xie , Jian Yang

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

Despite the great empirical success of deep reinforcement learning, its theoretical foundation is less well understood. In this work, we make the first attempt to theoretically understand the deep Q-network (DQN) algorithm (Mnih et al.,…

Machine Learning · Computer Science 2020-02-25 Jianqing Fan , Zhaoran Wang , Yuchen Xie , Zhuoran Yang

The problem of estimating a linear functional based on observational data is canonical in both the causal inference and bandit literatures. We analyze a broad class of two-stage procedures that first estimate the treatment effect function,…

Statistics Theory · Mathematics 2022-09-28 Wenlong Mou , Martin J. Wainwright , Peter L. Bartlett