English
Related papers

Related papers: Policy Gradient Bounds in Multitask LQR

200 papers

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

We study the global linear convergence of policy gradient (PG) methods for finite-horizon continuous-time exploratory linear-quadratic control (LQC) problems. The setting includes stochastic LQC problems with indefinite costs and allows…

Optimization and Control · Mathematics 2024-03-05 Michael Giegrich , Christoph Reisinger , Yufei Zhang

Cooperative multi-agent reinforcement learning (MARL) is making rapid progress for solving tasks in a grid world and real-world scenarios, in which agents are given different attributes and goals, resulting in different behavior through the…

Multiagent Systems · Computer Science 2022-07-13 Siyi Hu , Chuanlong Xie , Xiaodan Liang , Xiaojun Chang

We develop a neural-network framework for multi-period risk--reward stochastic control problems with constrained two-step feedback policies that may be discontinuous in the state. We allow a broad class of objectives built on a…

Computational Finance · Quantitative Finance 2026-03-09 Chang Chen , Duy-Minh Dang

Stability is one of the most fundamental requirements for systems synthesis. In this paper, we address the stabilization problem for unknown linear systems via policy gradient (PG) methods. We leverage a key feature of PG for Linear…

Optimization and Control · Mathematics 2021-12-20 Feiran Zhao , Xingyun Fu , Keyou You

In this paper, we study the control of dynamical systems under temporal logic task specifications using gradient-based methods relying on quantitative measures that express the extent to which the tasks are satisfied. A class of controllers…

Systems and Control · Electrical Eng. & Systems 2019-09-06 Peter Varnai , Dimos V. Dimarogonas

This paper addresses a critical societal consideration in the application of Reinforcement Learning (RL): ensuring equitable outcomes across different demographic groups in multi-task settings. While previous work has explored fairness in…

Machine Learning · Computer Science 2025-03-12 Kefan Song , Runnan Jiang , Rohan Chandra , Shangtong Zhang

Bilevel optimization involves a hierarchical structure where one problem is nested within another, leading to complex interdependencies between levels. We propose a single-loop, tuning-free algorithm that guarantees anytime feasibility,…

Optimization and Control · Mathematics 2025-08-15 Sina Sharifi , Erfan Yazdandoost Hamedani , Mahyar Fazlyab

This paper studies convergence properties of inexact iterative solution schemes for bilevel optimization problems. Bilevel optimization problems emerge in control-aware design optimization, where the system design parameters are optimized…

Optimization and Control · Mathematics 2024-03-26 Torbjørn Cunis Ilya Kolmanovsky

This paper proposes a scalable distributed policy gradient method and proves its convergence to near-optimal solution in multi-agent linear quadratic networked systems. The agents engage within a specified network under local communication…

Multiagent Systems · Computer Science 2024-03-06 Yuzi Yan , Yuan Shen

In recent years, as the demand for low energy and high performance computing has steadily increased, heterogeneous computing has emerged as an important and promising solution. Because most workloads can typically run most efficiently on…

Performance · Computer Science 2017-12-11 Zhuo Chen , Diana Marculescu

Spectral risk objectives - also called $L$-risks - allow for learning systems to interpolate between optimizing average-case performance (as in empirical risk minimization) and worst-case performance on a task. We develop stochastic…

Machine Learning · Statistics 2022-12-13 Ronak Mehta , Vincent Roulet , Krishna Pillutla , Lang Liu , Zaid Harchaoui

We consider the static output feedback control for Linear Quadratic Regulator problems with structured constraints under the assumption that system parameters are unknown. To solve the problem in the model free setting, we propose the…

Optimization and Control · Mathematics 2023-03-21 Shokichi Takakura , Kazuhiro Sato

Trace norm regularization is a popular method of multitask learning. We give excess risk bounds with explicit dependence on the number of tasks, the number of examples per task and properties of the data distribution. The bounds are…

Machine Learning · Statistics 2013-01-15 Andreas Maurer , Massimiliano Pontil

Multi-task post-training of large language models (LLMs) is typically performed by mixing datasets from different tasks and optimizing them jointly. This approach implicitly assumes that all tasks contribute gradients of similar magnitudes;…

Reinforcement Learning (RL) robot controllers usually aggregate many task objectives into one scalar reward. While large-scale proximal policy optimisation (PPO) has enabled impressive results such as robust robot locomotion in the real…

Robotics · Computer Science 2025-09-19 Humphrey Munn , Brendan Tidd , Peter Böhm , Marcus Gallagher , David Howard

The goal of multi-task learning is to learn diverse tasks within a single unified network. As each task has its own unique objective function, conflicts emerge during training, resulting in negative transfer among them. Earlier research…

Machine Learning · Computer Science 2024-06-06 Wooseong Jeong , Kuk-Jin Yoon

Continually solving new, unsolved tasks is the key to learning diverse behaviors. Through reinforcement learning (RL), we have made massive strides towards solving tasks that have a single goal. However, in the multi-task domain, where an…

Machine Learning · Computer Science 2020-06-18 Yunzhi Zhang , Pieter Abbeel , Lerrel Pinto

Likelihood-based policy gradient methods are the dominant approach for training robot control policies from rewards. These methods rely on differentiable action likelihoods, which constrain policy outputs to simple distributions like…

We investigate a Linear-Quadratic-Gaussian (LQG) control and sensing co-design problem, where one jointly designs sensing and control policies. We focus on the realistic case where the sensing design is selected among a finite set of…

Optimization and Control · Mathematics 2020-05-20 Vasileios Tzoumas , Luca Carlone , George J. Pappas , Ali Jadbabaie