English
Related papers

Related papers: Completion vs Optimality: Policy Gradient in Long-…

200 papers

This paper provides a theoretical and numerical investigation of a penalty decomposition scheme for the solution of optimization problems with geometric constraints. In particular, we consider some situations where parts of the constraints…

Optimization and Control · Mathematics 2023-03-23 Matteo Lapucci , Christian Kanzow

Recently there has been an increasing interest in primal-dual methods for model predictive control (MPC), which require minimizing the (augmented) Lagrangian at each iteration. We propose a novel first order primal-dual method, termed…

Optimization and Control · Mathematics 2020-12-21 Yue Yu , Purnanand Elango , Behçet Açikmeşe

We introduce a novel policy learning method that integrates analytical gradients from differentiable environments with the Proximal Policy Optimization (PPO) algorithm. To incorporate analytical gradients into the PPO framework, we…

Machine Learning · Computer Science 2023-12-15 Sanghyun Son , Laura Yu Zheng , Ryan Sullivan , Yi-Ling Qiao , Ming C. Lin

Predictive control is frequently used for control problems involving constraints. Being an optimization based technique utilizing a user specified so-called stage cost, performance properties, i.e., bounds on the infinite horizon…

Systems and Control · Electrical Eng. & Systems 2022-09-09 Lukas Beckenbach , Stefan Streif

We consider a smoothed online convex optimization (SOCO) problem with predictions, where the learner has access to a finite lookahead window of time-varying stage costs, but suffers a switching cost for changing its actions at each stage.…

Optimization and Control · Mathematics 2023-10-16 Spandan Senapati , Ashwin Shenai , Ketan Rajawat

This paper is devoted to a study of infinite horizon optimal control problems with time discounting and time averaging criteria in discrete time. It is known that these problems are related to certain infinite-dimensional linear programming…

Optimization and Control · Mathematics 2023-04-26 Ilya Shvartsman

We use one-step conditional risk mappings to formulate a risk averse version of a total cost problem on a controlled Markov process in discrete time infinite horizon. The nonnegative one step costs are assumed to be lower semi-continuous…

Optimization and Control · Mathematics 2018-06-05 Kerem Ugurlu

We address the problem of simultaneously learning and control in an online receding horizon control setting. We consider the control of an unknown linear dynamical system with general cost functions and affine constraints on the control…

Optimization and Control · Mathematics 2022-11-02 Deepan Muthirayan , Jianjun Yuan , Pramod P. Khargonekar

We study projection-free methods for functional constrained optimization with convex or smooth nonconvex objectives. Such problems arise in applications such as portfolio optimization and radiation therapy planning, where risk-aware…

Optimization and Control · Mathematics 2026-05-12 Yi Cheng , Guanghui Lan , Saeed Masiha , H. Edwin Romeijn

Reinforcement Learning, particularly through policy gradient methods, has played a central role in enabling reasoning capabilities of Large Language Models. However, the optimization stability of policy gradients in this setting remains…

Machine Learning · Computer Science 2026-03-03 Luckeciano C. Melo , Alessandro Abate , Yarin Gal

Proximal Policy Optimization (PPO) dominates reinforcement learning and LLM alignment but relies on a "hard clipping" mechanism that discards valuable gradients. Conversely, unconstrained methods like SPO expose the optimization to…

Artificial Intelligence · Computer Science 2026-05-07 Yiheng Zhang , Yiming Wang , Kaiyan Zhao , Zhenglin Wan , Jiayu Chen , Leong Hou U

We introduce the receding-horizon policy gradient (RHPG) algorithm, the first PG algorithm with provable global convergence in learning the optimal linear estimator designs, i.e., the Kalman filter (KF). Notably, the RHPG algorithm does not…

Optimization and Control · Mathematics 2023-09-12 Xiangyuan Zhang , Saviz Mowlavi , Mouhacine Benosman , Tamer Başar

Customizing an LLM judge to a specific task or domain often involves optimizing its prompt across multiple evaluation criteria simultaneously. Textual gradient methods automate this for a single judge criterion, however they produce…

Computation and Language · Computer Science 2026-05-26 Parth Darshan , Abhishek Divekar

Off-policy estimation for long-horizon problems is important in many real-life applications such as healthcare and robotics, where high-fidelity simulators may not be available and on-policy evaluation is expensive or impossible. Recently,…

Machine Learning · Computer Science 2020-03-26 Ali Mousavi , Lihong Li , Qiang Liu , Denny Zhou

Under mild regularity conditions, gradient-based methods converge globally to a critical point in the single-loss setting. This is known to break down for vanilla gradient descent when moving to multi-loss optimization, but can we hope to…

Optimization and Control · Mathematics 2021-01-19 Alistair Letcher

Once failure is irreversible, continuation payoffs cannot be meaningfully aggregated across strategies that differ in their survival properties. Standard scalar evaluation sidesteps this by arbitrarily completing payoffs beyond termination,…

Theoretical Economics · Economics 2026-02-10 Nicholas H. Kirk

Optimization with nonnegative orthogonality constraints has wide applications in machine learning and data sciences. It is NP-hard due to some combinatorial properties of the constraints. We first propose an equivalent optimization…

Optimization and Control · Mathematics 2021-01-01 Bo Jiang , Xiang Meng , Zaiwen Wen , Xiaojun Chen

When training autoregressive models to forecast dynamical systems, a critical question arises: how far into the future should the model be trained to predict? Too short a horizon may miss long-term trends, while too long a horizon can…

Machine Learning · Computer Science 2025-06-23 Pau Vilimelis Aceituno , Jack William Miller , Noah Marti , Youssef Farag , Victor Boussange

A class of infinite horizon optimal control problems involving mixed quasi-norms of $L^p$-type cost functionals for the controls is discussed. These functionals enhance sparsity and switching properties of the optimal controls. The…

Optimization and Control · Mathematics 2020-11-17 Dante Kalise , Karl Kunisch , Zhiping Rao

Reinforcement Learning Fine-Tuning (RLFT) has achieved notable success in tasks with objectively verifiable answers (e.g., code generation, mathematical reasoning), yet struggles with open-ended subjective tasks like role-playing dialogue.…

Computation and Language · Computer Science 2025-08-13 Xinge Ye , Rui Wang , Yuchuan Wu , Victor Ma , Feiteng Fang , Fei Huang , Yongbin Li