English
Related papers

Related papers: Beyond dynamic programming

200 papers

We consider finite and infinite horizon dynamic programming problems, where the control at each stage consists of several distinct decisions, each one made by one of several agents. We introduce an approach, whereby at every stage, each…

Machine Learning · Computer Science 2020-04-15 Dimitri Bertsekas

Solving complex problems using reinforcement learning necessitates breaking down the problem into manageable tasks and learning policies to solve these tasks. These policies, in turn, have to be controlled by a master policy that takes…

Artificial Intelligence · Computer Science 2022-08-09 Ambedkar Dukkipati , Rajarshi Banerjee , Ranga Shaarad Ayyagari , Dhaval Parmar Udaybhai

Policy optimization methods have shown great promise in solving complex reinforcement and imitation learning tasks. While model-free methods are broadly applicable, they often require many samples to optimize complex policies. Model-based…

Artificial Intelligence · Computer Science 2017-11-23 Daniel Levy , Stefano Ermon

Whenever a clinician reflects on the efficacy of a sequence of treatment decisions for a patient, they may try to identify critical time steps where, had they made different decisions, the patient's health would have improved. While recent…

Machine Learning · Computer Science 2023-11-07 Stratis Tsirtsis , Manuel Gomez-Rodriguez

Hierarchical reinforcement learning (HRL) proposes to solve difficult tasks by performing decision-making and control at successively higher levels of temporal abstraction. However, off-policy HRL often suffers from the problem of a…

Machine Learning · Computer Science 2023-03-14 Vivienne Huiling Wang , Joni Pajarinen , Tinghuai Wang , Joni-Kristian Kämäräinen

We consider the problem of continuous-time policy evaluation. This consists in learning through observations the value function associated with an uncontrolled continuous-time stochastic dynamic and a reward function. We propose two…

Machine Learning · Computer Science 2023-06-08 Ziad Kobeissi , Francis Bach

We introduce a new approach for the numerical pricing of American options. The main idea is to choose a finite number of suitable excessive functions (randomly) and to find the smallest majorant of the gain function in the span of these…

Computational Finance · Quantitative Finance 2013-10-17 Sören Christensen

We study an optimal execution problem in the infinite horizon setup. Our financial market is given by the Black-Scholes model with a linear price impact. The main novelty of the current note is that we study the constrained case where the…

Mathematical Finance · Quantitative Finance 2024-11-20 Yan Dolinsky

Curriculum learning is a training strategy that sorts the training examples by some measure of their difficulty and gradually exposes them to the learner to improve the network performance. Motivated by our insights from implicit curriculum…

Machine Learning · Computer Science 2021-07-28 Vinu Sankar Sadasivan , Anirban Dasgupta

We introduce a model of infinite horizon linear dynamic optimization and obtain results concerning existence of solution and satisfaction of the competitive condition and transversality condition being unconditionally sufficient for…

Optimization and Control · Mathematics 2025-06-23 Somdeb Lahiri

This paper proposes a policy-based deep reinforcement learning hyper-heuristic framework for solving the Job Shop Scheduling Problem. The hyper-heuristic agent learns to switch scheduling rules based on the system state dynamically. We…

Artificial Intelligence · Computer Science 2026-01-19 Sofiene Lassoued , Asrat Gobachew , Stefan Lier , Andreas Schwung

There is growing interest in termination reasoning for non-linear programs and, meanwhile, recent dynamic strategies have shown they are able to infer invariants for such challenging programs. These advances led us to hypothesize that…

Programming Languages · Computer Science 2020-10-13 Ton Chanh Le , Timos Antonopoulos , Parisa Fathololumi , Eric Koskinen , ThanhVu Nguyen

Path Integral Control methods were developed for stochastic optimal control covering a wide class of finite horizon formulations with control affine nonlinear dynamics. Characteristic for this class is that the HJB equation is linear and…

Optimization and Control · Mathematics 2021-03-08 Tom Lefebvre , Guillaume Crevecoeur

We present new algorithms for inverse reinforcement learning (IRL, or inverse optimal control) in convex optimization settings. We argue that finite-space IRL can be posed as a convex quadratic program under a Bayesian inference framework…

Machine Learning · Computer Science 2013-01-22 Qifeng Qiao , Peter A. Beling

As autonomous robots move into complex, dynamic real-world environments, they must learn to navigate safely in real time, yet anticipating all possible behaviors is infeasible. We propose a composable, model-free reinforcement learning…

Robotics · Computer Science 2026-02-16 Xinhuan Sang , Abdelrahman Abdelgawad , Roberto Tron

This paper studies an optimal stochastic impulse control problem in a finite horizon with a decision lag, by which we mean that after an impulse is made, a fixed number units of time has to be elapsed before the next impulse is allowed to…

Optimization and Control · Mathematics 2021-02-09 Chang Li , Jiongmin Yong

Diffusion and flow matching have emerged as expressive policy classes in reinforcement learning, but their reliance on multi-step denoising imposes substantial computational overhead at inference time, which is particularly problematic in…

Machine Learning · Computer Science 2026-05-25 Kyungyoon Kim , Donghyeon Ki , Hee-Jun Ahn , Byung-Jun Lee

We propose two novel numerical schemes for approximate implementation of the dynamic programming~(DP) operation concerned with finite-horizon, optimal control of discrete-time systems with input-affine dynamics. The proposed algorithms…

Optimization and Control · Mathematics 2022-03-18 M. A. S. Kolarijani , P. Mohajerin Esfahani

We consider the sequential decision-making problem where the mean outcome is a non-linear function of the chosen action. Compared with the linear model, two curious phenomena arise in non-linear models: first, in addition to the "learning…

Machine Learning · Statistics 2024-01-11 Nived Rajaraman , Yanjun Han , Jiantao Jiao , Kannan Ramchandran

Oftentimes, environments for sequential decision-making problems can be quite sparse in the provision of evaluative feedback to guide reinforcement-learning agents. In the extreme case, long trajectories of behavior are merely punctuated…

Machine Learning · Computer Science 2023-08-22 Akash Velu , Skanda Vaidyanath , Dilip Arumugam