English
Related papers

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

200 papers

Recently, reinforcement learning (RL) is receiving more and more attentions due to its successful demonstrations outperforming human performance in certain challenging tasks. In our recent paper `primal-dual Q-learning framework for LQR…

Optimization and Control · Mathematics 2018-11-22 Donghwan Lee , Jianghai Hu

Double Q-learning is a classical method for reducing overestimation bias, which is caused by taking maximum estimated values in the Bellman operation. Its variants in the deep Q-learning paradigm have shown great promise in producing…

Machine Learning · Computer Science 2022-01-17 Zhizhou Ren , Guangxiang Zhu , Hao Hu , Beining Han , Jianglun Chen , Chongjie Zhang

Optimal control theory and machine learning techniques are combined to formulate and solve in closed form an optimal control formulation of online learning from supervised examples with regularization of the updates. The connections with…

Optimization and Control · Mathematics 2016-12-15 Giorgio Gnecco , Alberto Bemporad , Marco Gori , Marcello Sanguineti

Based on the complete-lattice approach, a new Lagrangian duality theory for set-valued optimization problems is presented. In contrast to previous approaches, set-valued versions for the known scalar formulas involving infimum and supremum…

Optimization and Control · Mathematics 2024-01-26 Andreas H. Hamel , Andreas Löhne

Q-learning is a stochastic approximation version of the classic value iteration. The literature has established that Q-learning suffers from both maximization bias and slower convergence. Recently, multi-step algorithms have shown practical…

Machine Learning · Computer Science 2024-07-03 Antony Vijesh , Shreyas S R

Q-functions are widely used in discrete-time learning and control to model future costs arising from a given control policy, when the initial state and input are given. Although some of their properties are understood, Q-functions…

Optimization and Control · Mathematics 2019-02-21 Joseph Warrington

State-of-the-art techniques for simultaneous localization and mapping (SLAM) employ iterative nonlinear optimization methods to compute an estimate for robot poses. While these techniques often work well in practice, they do not provide…

Robotics · Computer Science 2015-07-21 Luca Carlone , David Rosen , Giuseppe Calafiore , John Leonard , Frank Dellaert

In the article we present a general theory of augmented Lagrangian functions for cone constrained optimization problems that allows one to study almost all known augmented Lagrangians for cone constrained programs within a unified…

Optimization and Control · Mathematics 2024-09-11 M. V. Dolgopolik

We study the problem of building an efficient learning system. Efficient learning processes information in the least time, i.e., building a system that reaches a desired error threshold with the least number of observations. Building upon…

Machine Learning · Computer Science 2025-09-26 Siyuan Guo , Bernhard Schölkopf

We develop an efficient method for solving non-convex constrained optimization problems that are pervasive in economics. The optimal solution to these problems often involves randomization. We employ a Lagrangian framework and prove that…

Theoretical Economics · Economics 2026-05-07 Chengfeng Shen , Felix Kübler , Yucheng Yang , Zhennan Zhou

Value function learning plays a central role in many state-of-the-art reinforcement-learning algorithms. Many popular algorithms like Q-learning do not optimize any objective function, but are fixed-point iterations of some variant of…

Machine Learning · Computer Science 2020-01-10 Yihao Feng , Lihong Li , Qiang Liu

Full-sampling (e.g., Q-learning) and pure-expectation (e.g., Expected Sarsa) algorithms are efficient and frequently used techniques in reinforcement learning. Q$(\sigma,\lambda)$ is the first approach unifies them with eligibility trace…

Machine Learning · Computer Science 2019-09-09 Long Yang , Yu Zhang , Qian Zheng , Pengfei Li , Gang Pan

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…

Machine Learning · Computer Science 2017-07-26 Kun Li , Yanan Sui , Joel W. Burdick

In recent years there has been a collective research effort to find new formulations of reinforcement learning that are simultaneously more efficient and more amenable to analysis. This paper concerns one approach that builds on the linear…

Optimization and Control · Mathematics 2022-10-19 Fan Lu , Prashant Mehta , Sean Meyn , Gergely Neu

We solve large-scale mixed-integer linear programs (MILPs) via distributed asynchronous saddle point computation. This is motivated by the MILPs being able to model problems in multi-agent autonomy, e.g., task assignment problems and…

Optimization and Control · Mathematics 2022-11-23 Luke Fina , Matthew Hale

Regularized Markov Decision Processes serve as models of sequential decision making under uncertainty wherein the decision maker has limited information processing capacity and/or aversion to model ambiguity. With functional approximation,…

Artificial Intelligence · Computer Science 2025-02-11 Jiachen Xi , Alfredo Garcia , Petar Momcilovic

We propose a new reinforcement learning algorithm derived from a regularized linear-programming formulation of optimal control in MDPs. The method is closely related to the classic Relative Entropy Policy Search (REPS) algorithm of Peters…

Machine Learning · Computer Science 2021-03-01 Joan Bas-Serrano , Sebastian Curi , Andreas Krause , Gergely Neu

We study the convergence of $Q$-learning with linear function approximation. Our key contribution is the introduction of a novel multi-Bellman operator that extends the traditional Bellman operator. By exploring the properties of this…

Machine Learning · Computer Science 2023-10-02 Diogo S. Carvalho , Pedro A. Santos , Francisco S. Melo

In this paper, we design a theoretical framework allowing to apply model predictive control on hybrid systems. For this, we develop a theory of approximate dynamic programming by leveraging the concept of alternating simulation. We show how…

Optimization and Control · Mathematics 2020-11-24 Benoît Legat , Raphaël M. Jungers , Jean Bouchat

The Q-learning algorithm is known to be affected by the maximization bias, i.e. the systematic overestimation of action values, an important issue that has recently received renewed attention. Double Q-learning has been proposed as an…

Machine Learning · Computer Science 2021-02-03 Rong Zhu , Mattia Rigotti
‹ Prev 1 2 3 10 Next ›