English
Related papers

Related papers: Asynchronous Parallel Policy Gradient Methods for …

200 papers

We consider the continuous-time Linear-Quadratic-Regulator (LQR) problem in terms of optimizing a real-valued matrix function over the set of feedback gains. The results developed are in parallel to those in Bu et al. [1] for discrete-time…

Systems and Control · Electrical Eng. & Systems 2020-06-17 Jingjing Bu , Afshin Mesbahi , Mehran Mesbahi

With the outstanding performance of policy gradient (PG) method in the reinforcement learning field, the convergence theory of it has aroused more and more interest recently. Meanwhile, the significant importance and abundant theoretical…

Optimization and Control · Mathematics 2024-04-19 Xinpei Zhang , Guangyan Jia

Stochastic gradient descent~(SGD) and its variants have become more and more popular in machine learning due to their efficiency and effectiveness. To handle large-scale problems, researchers have recently proposed several parallel SGD…

Machine Learning · Statistics 2015-08-25 Shen-Yi Zhao , Wu-Jun Li

Gradient descent, and coordinate descent in particular, are core tools in machine learning and elsewhere. Large problem instances are common. To help solve them, two orthogonal approaches are known: acceleration and parallelism. In this…

Optimization and Control · Mathematics 2018-08-16 Richard Cole , Yixin Tao

Distributed training and increasing the gradient update frequency are practical strategies to accelerate learning and improve performance, but both exacerbate a central challenge: \textit{policy lag}, which is the mismatch between the…

This paper studies an infinite horizon optimal control problem for discrete-time linear system and quadratic criteria, both with random parameters which are independent and identically distributed with respect to time. In this general…

Optimization and Control · Mathematics 2024-03-04 Deyue Li

To improve the efficiency of reinforcement learning (RL), we propose a novel asynchronous federated reinforcement learning (FedRL) framework termed AFedPG, which constructs a global model through collaboration among $N$ agents using policy…

Machine Learning · Computer Science 2025-01-27 Guangchen Lan , Dong-Jun Han , Abolfazl Hashemi , Vaneet Aggarwal , Christopher G. Brinton

We propose controller synthesis for state regulation problems in which a human operator shares control with an autonomy system, running in parallel. The autonomy system continuously improves over human action, with minimal intervention, and…

Systems and Control · Computer Science 2019-09-23 Murad Abu-Khalaf , Sertac Karaman , Daniela Rus

Reinforcement learning (RL) is attracting increasing interests in autonomous driving due to its potential to solve complex classification and control problems. However, existing RL algorithms are rarely applied to real vehicles for two…

Machine Learning · Computer Science 2020-03-04 Lu Wen , Jingliang Duan , Shengbo Eben Li , Shaobing Xu , Huei Peng

Policy gradient (PG) algorithms have been widely used in reinforcement learning (RL). However, PG algorithms rely on exploiting the value function being learned with the first-order update locally, which results in limited sample…

Machine Learning · Computer Science 2021-07-06 Hao Sun , Ziping Xu , Yuhang Song , Meng Fang , Jiechao Xiong , Bo Dai , Bolei Zhou

We investigate the problem of learning linear quadratic regulators (LQR) in a multi-task, heterogeneous, and model-free setting. We characterize the stability and personalization guarantees of a policy gradient-based (PG) model-agnostic…

Optimization and Control · Mathematics 2024-06-04 Leonardo F. Toso , Donglin Zhan , James Anderson , Han Wang

This paper proposes a general formulation for temporal parallelisation of dynamic programming for optimal control problems. We derive the elements and associative operators to be able to use parallel scans to solve these problems with…

Optimization and Control · Mathematics 2022-01-25 Simo Särkkä , Ángel F. García-Fernández

We present a continuous-time equivalent to the well-known iterative linear-quadratic algorithm including an implementation of a backtracking line-search policy and a novel regularization approach based on the necessary conditions in the…

Systems and Control · Electrical Eng. & Systems 2025-05-22 Juraj Lieskovský , Jaroslav Bušek , Tomáš Vyhlídal

We propose a parallel adaptive constraint-tightening approach to solve a linear model predictive control problem for discrete-time systems, based on inexact numerical optimization algorithms and operator splitting methods. The underlying…

Optimization and Control · Mathematics 2015-03-24 Laura Ferranti , Tamas Keviczky

Action-constrained reinforcement learning (ACRL) is a popular approach for solving safety-critical and resource-allocation related decision making problems. A major challenge in ACRL is to ensure agent taking a valid action satisfying…

Machine Learning · Computer Science 2024-02-09 Janaka Chathuranga Brahmanage , Jiajing Ling , Akshat Kumar

Nonlinear control systems with partial information to the decision maker are prevalent in a variety of applications. As a step toward studying such nonlinear systems, this work explores reinforcement learning methods for finding the optimal…

Machine Learning · Computer Science 2025-04-11 Yinbin Han , Meisam Razaviyayn , Renyuan Xu

The growing interest for high dimensional and functional data analysis led in the last decade to an important research developing a consequent amount of techniques. Parallelized algorithms, which consist in distributing and treat the data…

Statistics Theory · Mathematics 2017-10-24 Antoine Godichon-Baggioni , Sofiane Saadane

Despite extreme sample inefficiency, on-policy reinforcement learning, aka policy gradients, has become a fundamental tool in decision-making problems. With the recent advances in GPU-driven simulation, the ability to collect large amounts…

Machine Learning · Computer Science 2024-07-30 Jayesh Singla , Ananye Agarwal , Deepak Pathak

As datasets continue to increase in size and multi-core computer architectures are developed, asynchronous parallel optimization algorithms become more and more essential to the field of Machine Learning. Unfortunately, conducting the…

Optimization and Control · Mathematics 2019-03-26 Rémi Leblond , Fabian Pedregosa , Simon Lacoste-Julien

Flow $Q$-learning has recently been introduced to integrate learning from expert demonstrations into an actor-critic structure. Central to this innovation is the ``the one-step policy'' network, which is optimized through a $Q$-function…

Systems and Control · Electrical Eng. & Systems 2025-11-17 Farnaz Adib Yaghmaie , Arunava Naha