English
Related papers

Related papers: Beyond dynamic programming

200 papers

In this work we present a novel approach to hierarchical reinforcement learning for linearly-solvable Markov decision processes. Our approach assumes that the state space is partitioned, and the subtasks consist in moving between the…

Machine Learning · Computer Science 2024-06-04 Guillermo Infante , Anders Jonsson , Vicenç Gómez

Adaptive dynamic programming is a collective term for a variety of approaches to infinite-horizon optimal control. Common to all approaches is approximation of the infinite-horizon cost function based on dynamic programming philosophy.…

Optimization and Control · Mathematics 2020-07-09 Pavel Osinenko , Thomas Göhrt , Grigory Devadze , Stefan Streif

We propose a formulation of the stochastic cutting stock problem as a discounted infinite-horizon Markov decision process. At each decision epoch, given current inventory of items, an agent chooses in which patterns to cut objects in stock…

Optimization and Control · Mathematics 2022-06-29 Anselmo R. Pitombeira-Neto , Arthur H. Fonseca Murta

We study a specific class of finite-horizon mean field optimal stopping problems by means of the dynamic programming approach. In particular, we consider problems where the state process is not affected by the stopping time. Such problems…

Optimization and Control · Mathematics 2025-03-07 Andrea Cosso , Laura Perelli

Policy learning utilizing observational data is pivotal across various domains, with the objective of learning the optimal treatment assignment policy while adhering to specific constraints such as fairness, budget, and simplicity. This…

Methodology · Statistics 2023-10-12 Pan Zhao , Antoine Chambaz , Julie Josse , Shu Yang

We examine the problem of two-point boundary optimal control of nonlinear systems over finite-horizon time periods with unknown model dynamics by employing reinforcement learning. We use techniques from singular perturbation theory to…

Optimization and Control · Mathematics 2023-06-12 Vasanth Reddy , Hoda Eldardiry , Almuatazbellah Boker

In many scientific and engineering problems, noise and nonlinearity are unavoidable, which could induce interesting mathematical problem such as transition phenomena. This paper focuses on efficiently discovering the most probable…

Optimization and Control · Mathematics 2023-06-08 Jin Guo , Ting Gao , Peng Zhang , Jiequn Han , Jinqiao Duan

We consider reinforcement learning (RL) methods in offline domains without additional online data collection, such as mobile health applications. Most of existing policy optimization algorithms in the computer science literature are…

Machine Learning · Statistics 2022-07-28 Chengchun Shi , Shikai Luo , Yuan Le , Hongtu Zhu , Rui Song

We propose a machine learning algorithm for solving finite-horizon stochastic control problems based on a deep neural network representation of the optimal policy functions. The algorithm has three features: (1) It can solve…

General Economics · Economics 2024-12-09 Xianhua Peng , Steven Kou , Lekang Zhang

An iterative learning algorithm is presented for continuous-time linear-quadratic optimal control problems where the system is externally symmetric with unknown dynamics. Both finite-horizon and infinite-horizon problems are considered. It…

Optimization and Control · Mathematics 2025-10-10 Hamed Taghavian , Florian Dorfler , Mikael Johansson

We explore how to build a vector field from the various functions involved in a given mathematical program, and show that locally-stable equilibria of the underlying dynamical system are precisely the local solutions of the optimization…

Optimization and Control · Mathematics 2017-06-09 Pablo Pedregal

This paper investigates an infinite-horizon linear quadratic stochastic (LQS) optimal control problem for a class of continuous-time stochastic systems. By employing the technique of adaptive dynamic programming (ADP), we propose a novel…

Optimization and Control · Mathematics 2022-10-11 Heng Zhang

We consider the problem of reinforcement learning when provided with (1) a baseline control policy and (2) a set of constraints that the learner must satisfy. The baseline policy can arise from demonstration data or a teacher agent and may…

Machine Learning · Computer Science 2021-07-13 Tsung-Yen Yang , Justinian Rosca , Karthik Narasimhan , Peter J. Ramadge

We adapt the ideas underlying the success of Deep Q-Learning to the continuous action domain. We present an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces. Using…

In this article, we discuss two algorithms tailored to discrete-time deterministic finite-horizon nonlinear optimal control problems or so-called deterministic trajectory optimization problems. Both algorithms can be derived from an…

Optimization and Control · Mathematics 2024-12-10 Mohammad Mahmoudi Filabadi , Tom Lefebvre , Guillaume Crevecoeur

We consider a general formulation of the Principal-Agent problem with a lump-sum payment on a finite horizon, providing a systematic method for solving such problems. Our approach is the following: we first find the contract that is optimal…

Optimization and Control · Mathematics 2017-01-10 Jakša Cvitanić , Dylan Possamaï , Nizar Touzi

Standard reinforcement learning (RL) aims to find an optimal policy that identifies the best action for each state. However, in healthcare settings, many actions may be near-equivalent with respect to the reward (e.g., survival). We…

Machine Learning · Computer Science 2020-07-27 Shengpu Tang , Aditya Modi , Michael W. Sjoding , Jenna Wiens

We introduce a class of learning problems where the agent is presented with a series of tasks. Intuitively, if there is relation among those tasks, then the information gained during execution of one task has value for the execution of…

Machine Learning · Computer Science 2012-09-06 Christos Dimitrakakis

Large language models excel at short-horizon reasoning tasks, but performance drops as reasoning horizon lengths increase. Existing approaches to combat this rely on inference-time scaffolding or costly step-level supervision, neither of…

The ability to compose learned skills to solve new tasks is an important property of lifelong-learning agents. In this work, we formalise the logical composition of tasks as a Boolean algebra. This allows us to formulate new tasks in terms…

Machine Learning · Computer Science 2020-10-16 Geraud Nangue Tasse , Steven James , Benjamin Rosman