English
Related papers

Related papers: Finite-Time Error Bounds for Greedy-GQ

200 papers

Greedy-GQ is an off-policy two timescale algorithm for optimal control in reinforcement learning. This paper develops the first finite-sample analysis for the Greedy-GQ algorithm with linear function approximation under Markovian noise. Our…

Machine Learning · Computer Science 2020-05-21 Yue Wang , Shaofeng Zou

Greedy-GQ is a value-based reinforcement learning (RL) algorithm for optimal control. Recently, the finite-time analysis of Greedy-GQ has been developed under linear function approximation and Markovian sampling, and the algorithm is shown…

Machine Learning · Computer Science 2021-03-31 Shaocong Ma , Ziyi Chen , Yi Zhou , Shaofeng Zou

Two timescale stochastic approximation (SA) has been widely used in value-based reinforcement learning algorithms. In the policy evaluation setting, it can model the linear and nonlinear temporal difference learning with gradient correction…

Machine Learning · Computer Science 2020-11-11 Tengyu Xu , Yingbin Liang

In this paper, we analyze the convergence rate of the gradient temporal difference learning (GTD) family of algorithms. Previous analyses of this class of algorithms use ODE techniques to prove asymptotic convergence, and to the best of our…

Machine Learning · Computer Science 2020-07-06 Bo Liu , Ji Liu , Mohammad Ghavamzadeh , Sridhar Mahadevan , Marek Petrik

Policy evaluation in reinforcement learning is often conducted using two-timescale stochastic approximation, which results in various gradient temporal difference methods such as GTD(0), GTD2, and TDC. Here, we provide convergence rate…

Machine Learning · Computer Science 2019-12-05 Gal Dalal , Balazs Szorenyi , Gugan Thoppe

It is known that greedy methods perform well for maximizing monotone submodular functions. At the same time, such methods perform poorly in the face of non-monotonicity. In this paper, we show - arguably, surprisingly - that invoking the…

Machine Learning · Computer Science 2017-04-07 Moran Feldman , Christopher Harshaw , Amin Karbasi

Q-learning with neural network function approximation (neural Q-learning for short) is among the most prevalent deep reinforcement learning algorithms. Despite its empirical success, the non-asymptotic convergence rate of neural Q-learning…

Machine Learning · Computer Science 2020-03-05 Pan Xu , Quanquan Gu

Although Q-learning is one of the most successful algorithms for finding the best action-value function (and thus the optimal policy) in reinforcement learning, its implementation often suffers from large overestimation of Q-function values…

Machine Learning · Computer Science 2020-10-13 Huaqing Xiong , Lin Zhao , Yingbin Liang , Wei Zhang

We study sublinear time algorithms for estimating the size of maximum matching in graphs. Our main result is a $(\frac{1}{2}+\Omega(1))$-approximation algorithm which can be implemented in $O(n^{1+\epsilon})$ time, where $n$ is the number…

Data Structures and Algorithms · Computer Science 2022-06-28 Soheil Behnezhad , Mohammad Roghani , Aviad Rubinstein , Amin Saberi

In reinforcement learning (RL) , one of the key components is policy evaluation, which aims to estimate the value function (i.e., expected long-term accumulated reward) of a policy. With a good policy evaluation method, the RL algorithms…

Machine Learning · Computer Science 2018-09-25 Yue Wang , Wei Chen , Yuting Liu , Zhi-Ming Ma , Tie-Yan Liu

We devise a distributional variant of gradient temporal-difference (TD) learning. Distributional reinforcement learning has been demonstrated to outperform the regular one in the recent study \citep{bellemare2017distributional}. In the…

Machine Learning · Computer Science 2019-04-04 Chao Qu , Shie Mannor , Huan Xu

Given a finite family of functions, the goal of model selection aggregation is to construct a procedure that mimics the function from this family that is the closest to an unknown regression function. More precisely, we consider a general…

Statistics Theory · Mathematics 2012-12-13 Dong Dai , Philippe Rigollet , Tong Zhang

We study two time-scale linear stochastic approximation algorithms, which can be used to model well-known reinforcement learning algorithms such as GTD, GTD2, and TDC. We present finite-time performance bounds for the case where the…

Machine Learning · Computer Science 2019-07-16 Harsh Gupta , R. Srikant , Lei Ying

A deterministic approximation algorithm is presented for the maximization of non-monotone submodular functions over a ground set of size $n$ subject to cardinality constraint $k$; the algorithm is based upon the idea of interlacing two…

Data Structures and Algorithms · Computer Science 2019-10-28 Alan Kuhnle

We consider the problem of approximating a given element $f$ from a Hilbert space $\mathcal{H}$ by means of greedy algorithms and the application of such procedures to the regression problem in statistical learning theory. We improve on the…

Statistics Theory · Mathematics 2009-09-29 Andrew R. Barron , Albert Cohen , Wolfgang Dahmen , Ronald A. DeVore

In the first part of this paper, we prove that, under some natural non-degeneracy assumptions, the Greedy Parabolic Target-Following Method, based on {\em universal tangent direction} has a favorable local behavior. In view of its global…

Optimization and Control · Mathematics 2024-12-20 Yurii Nesterov

Decision Tree is a classic formulation of active learning: given $n$ hypotheses with nonnegative weights summing to 1 and a set of tests that each partition the hypotheses, output a decision tree using the provided tests that uniquely…

Data Structures and Algorithms · Computer Science 2019-10-23 Ray Li , Percy Liang , Stephen Mussmann

Temporal-difference learning with gradient correction (TDC) is a two time-scale algorithm for policy evaluation in reinforcement learning. This algorithm was initially proposed with linear function approximation, and was later extended to…

Machine Learning · Computer Science 2021-10-29 Yue Wang , Shaofeng Zou , Yi Zhou

Though quasi-Newton methods have been extensively studied in the literature, they either suffer from local convergence or use a series of line searches for global convergence which is not acceptable in the distributed setting. In this work,…

Optimization and Control · Mathematics 2023-12-01 Yubo Du , Keyou You

Motivated by recent work on stochastic gradient descent methods, we develop two stochastic variants of greedy algorithms for possibly non-convex optimization problems with sparsity constraints. We prove linear convergence in expectation to…

Numerical Analysis · Mathematics 2014-07-02 Nam Nguyen , Deanna Needell , Tina Woolf
‹ Prev 1 2 3 10 Next ›