English
Related papers

Related papers: Lagrangian Method for Q-Function Learning (with Ap…

200 papers

In a discounted reward Markov Decision Process (MDP), the objective is to find the optimal value function, i.e., the value function corresponding to an optimal policy. This problem reduces to solving a functional equation known as the…

Machine Learning · Computer Science 2019-06-17 Chandramouli Kamanchi , Raghuram Bharadwaj Diddigi , Shalabh Bhatnagar

Many problems in modern robotics can be addressed by modeling them as bilevel optimization problems. In this work, we leverage augmented Lagrangian methods and recent advances in automatic differentiation to develop a general-purpose…

Robotics · Computer Science 2019-07-03 Benoit Landry , Zachary Manchester , Marco Pavone

Hidden convexity is a powerful idea in optimization: under the right transformations, nonconvex problems that are seemingly intractable can be solved efficiently using convex optimization. We introduce the notion of a Lagrangian dual…

Optimization and Control · Mathematics 2025-11-07 Venkat Chandrasekaran , Timothy Duff , Jose Israel Rodriguez , Kevin Shu

Recently, large language models (LLMs) enhanced by self-reflection have achieved promising performance on machine translation. The key idea is guiding LLMs to generate translation with human-like feedback. However, existing self-reflection…

Computation and Language · Computer Science 2024-06-24 Andong Chen , Lianzhang Lou , Kehai Chen , Xuefeng Bai , Yang Xiang , Muyun Yang , Tiejun Zhao , Min Zhang

We study a stochastic first order primal-dual method for solving convex-concave saddle point problems over real reflexive Banach spaces using Bregman divergences and relative smoothness assumptions, in which we allow for stochastic error in…

Optimization and Control · Mathematics 2021-12-23 Antonio Silveti-Falls , Cesare Molinari , Jalal Fadili

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

The exploration-exploitation trade-off is among the central challenges of reinforcement learning. The optimal Bayesian solution is intractable in general. This paper studies to what extent analytic statements about optimal learning are…

Machine Learning · Statistics 2015-03-13 Philipp Hennig

We study the global convergence of generative adversarial imitation learning for linear quadratic regulators, which is posed as minimax optimization. To address the challenges arising from non-convex-concave geometry, we analyze the…

Machine Learning · Computer Science 2019-01-15 Qi Cai , Mingyi Hong , Yongxin Chen , Zhaoran Wang

A central challenge to many fields of science and engineering involves minimizing non-convex error functions over continuous, high dimensional spaces. Gradient descent or quasi-Newton methods are almost ubiquitously used to perform such…

Machine Learning · Computer Science 2014-05-29 Razvan Pascanu , Yann N. Dauphin , Surya Ganguli , Yoshua Bengio

This paper develops an online inverse reinforcement learning algorithm aimed at efficiently recovering a reward function from ongoing observations of an agent's actions. To reduce the computation time and storage space in reward estimation,…

Robotics · Computer Science 2017-08-01 Kun Li , Joel W. Burdick

Recently, a variety of new equivariant neural network model architectures have been proposed that generalize better over rotational and reflectional symmetries than standard models. These models are relevant to robotics because many…

Robotics · Computer Science 2021-11-01 Dian Wang , Robin Walters , Xupeng Zhu , Robert Platt

Value-based reinforcement learning (RL) methods like Q-learning have shown success in a variety of domains. One challenge in applying Q-learning to continuous-action RL problems, however, is the continuous action maximization (max-Q)…

Machine Learning · Computer Science 2020-03-03 Moonkyung Ryu , Yinlam Chow , Ross Anderson , Christian Tjandraatmadja , Craig Boutilier

The performance of most evolutionary metaheuristic algorithms relays on various operatives. One of them is the crossover operator, which is divided into two types: application dependent and application independent crossover operators. These…

Neural and Evolutionary Computing · Computer Science 2022-05-17 Aso M. Aladdin , Tarik A. Rashid

In this paper, we consider the linear programming (LP) formulation for deep reinforcement learning. The number of the constraints depends on the size of state and action spaces, which makes the problem intractable in large or continuous…

Optimization and Control · Mathematics 2021-05-21 Yongfeng Li , Mingming Zhao , Weijie Chen , Zaiwen Wen

The Knapsack Problem is a classic problem in combinatorial optimisation. Solving these problems may be computationally expensive. Recent years have seen a growing interest in the use of deep learning methods to approximate the solutions to…

Machine Learning · Computer Science 2023-12-07 Mitchell Keegan , Mahdi Abolghasemi

Duality between estimation and optimal control is a problem of rich historical significance. The first duality principle appears in the seminal paper of Kalman-Bucy, where the problem of minimum variance estimation is shown to be dual to a…

Optimization and Control · Mathematics 2019-10-28 Jin W. Kim , Prashant G. Mehta , Sean P. Meyn

Randomly initialized first-order optimization algorithms are the method of choice for solving many high-dimensional nonconvex problems in machine learning, yet general theoretical guarantees cannot rule out convergence to critical points of…

Optimization and Control · Mathematics 2018-09-28 Dar Gilboa , Sam Buchanan , John Wright

Training of neural networks amounts to nonconvex optimization problems that are typically solved by using backpropagation and (variants of) stochastic gradient descent. In this work we propose an alternative approach by viewing the training…

Optimization and Control · Mathematics 2022-04-14 Brecht Evens , Puya Latafat , Andreas Themelis , Johan Suykens , Panagiotis Patrinos

The impact of softmax on the value function itself in reinforcement learning (RL) is often viewed as problematic because it leads to sub-optimal value (or Q) functions and interferes with the contraction properties of the Bellman operator.…

Machine Learning · Computer Science 2019-05-21 Zhao Song , Ronald E. Parr , Lawrence Carin

In a recent joint work, the author has developed a modification of Newton's method, named New Q-Newton's method, which can avoid saddle points and has quadratic rate of convergence. While good theoretical convergence guarantee has not been…

Optimization and Control · Mathematics 2021-09-10 Tuyen Trung Truong