English
Related papers

Related papers: Is RL fine-tuning harder than regression? A PDE le…

200 papers

This work is devoted to the study of optimal control of stochastic functional differential equations (SFDEs) and its application to mathematical finance. By using the Dynkin formula and solution of the Dirichlet-Poisson problem, the…

Optimization and Control · Mathematics 2014-04-04 Edson A. Coayla-Teran , Anatoly Swishchuk

Diffusion models recently emerged as a powerful paradigm for recommender systems, offering state-of-the-art performance by modeling the generative process of user-item interactions. However, training such models from scratch is both…

Information Retrieval · Computer Science 2025-11-11 Yu Hou , Hua Li , Ha Young Kim , Won-Yong Shin

We treat infinite horizon optimal control problems by solving the associated stationary Hamilton-Jacobi-Bellman (HJB) equation numerically to compute the value function and an optimal feedback law. The dynamical systems under consideration…

Optimization and Control · Mathematics 2021-05-19 Mathias Oster , Leon Sallandt , Reinhold Schneider

Fine-tuning pretrained language models (PLMs) on downstream tasks has become common practice in natural language processing. However, most of the PLMs are vulnerable, e.g., they are brittle under adversarial attacks or imbalanced data,…

Computation and Language · Computer Science 2022-05-03 Shoujie Tong , Qingxiu Dong , Damai Dai , Yifan song , Tianyu Liu , Baobao Chang , Zhifang Sui

Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. They learn stochastic parametric (hyper)policies by either exploring in the space of actions or in the space of parameters.…

Machine Learning · Computer Science 2024-05-31 Alessandro Montenegro , Marco Mussi , Alberto Maria Metelli , Matteo Papini

In performative Reinforcement Learning (RL), an agent faces a policy-dependent environment: the reward and transition functions depend on the agent's policy. Prior work on performative RL has studied the convergence of repeated retraining…

Machine Learning · Computer Science 2025-05-12 Vasilis Pollatos , Debmalya Mandal , Goran Radanovic

We consider the problem of learning models for risk-sensitive reinforcement learning. We theoretically demonstrate that proper value equivalence, a method of learning models which can be used to plan optimally in the risk-neutral setting,…

Machine Learning · Computer Science 2023-12-05 Tyler Kastner , Murat A. Erdogdu , Amir-massoud Farahmand

We investigate the long time behavior of weakly dissipative semilinear Hamilton-Jacobi-Bellman (HJB) equations and the turnpike property for the corresponding stochastic control problems. To this aim, we develop a probabilistic approach…

Probability · Mathematics 2023-03-17 Giovanni Conforti

We consider the numerical solution of Hamilton-Jacobi-Bellman equations arising in stochastic control theory. We introduce a class of monotone approximation schemes relying on monotone interpolation. These schemes converge under very weak…

Numerical Analysis · Mathematics 2014-05-26 Kristian Debrabant , Espen R. Jakobsen

The focus of this article is studying an optimal control problem for branching diffusion processes. Initially, we introduce the problem in its strong formulation and expand it to include linearly growing drifts. Then, we present a relaxed…

Probability · Mathematics 2026-01-21 Antonio Ocello

We explore the approximation of feedback control of integro-differential equations containing a fractional Laplacian term. To obtain feedback control for the state variable of this nonlocal equation we use the Hamilton--Jacobi--Bellman…

Optimization and Control · Mathematics 2022-10-19 Alessandro Alla , Marta D'Elia , Christian Glusa , Hugo Oliveira

This paper studies an optimal dividend problem with a drawdown constraint in a Brownian motion model, requiring the dividend payout rate to remain above a fixed proportion of its historical maximum. This leads to a path-dependent stochastic…

Mathematical Finance · Quantitative Finance 2026-01-08 Chonghu Guan , Jiacheng Fan , Zuo Quan Xu

Convex Q-learning is a recent approach to reinforcement learning, motivated by the possibility of a firmer theory for convergence, and the possibility of making use of greater a priori knowledge regarding policy or value function structure.…

Optimization and Control · Mathematics 2022-10-18 Fan Lu , Joel Mathias , Sean Meyn , Karanjit Kalsi

We study a stochastic optimal control problem for a partially observed diffusion. By using the control randomization method in [4], we prove a corresponding randomized dynamic programming principle (DPP) for the value function, which is…

Probability · Mathematics 2016-09-12 Elena Bandini , Andrea Cosso , Marco Fuhrman , Huyên Pham

It has been recognized that the data generated by the denoising diffusion probabilistic model (DDPM) improves adversarial training. After two years of rapid development in diffusion models, a question naturally arises: can better diffusion…

Computer Vision and Pattern Recognition · Computer Science 2023-06-02 Zekai Wang , Tianyu Pang , Chao Du , Min Lin , Weiwei Liu , Shuicheng Yan

Robustness to modeling errors and uncertainties remains a central challenge in reinforcement learning (RL). In this work, we address this challenge by leveraging diffusion models to train robust RL policies. Diffusion models have recently…

Machine Learning · Computer Science 2025-12-03 Daniele Foffano , Alessio Russo , Alexandre Proutiere

Model-based Reinforcement Learning estimates the true environment through a world model in order to approximate the optimal policy. This family of algorithms usually benefits from better sample efficiency than their model-free counterparts.…

Machine Learning · Computer Science 2021-10-27 Valentin Charvet , Bjørn Sand Jensen , Roderick Murray-Smith

We study off-policy reinforcement learning for controlling continuous-time Markov diffusion processes with discrete-time observations and actions. We consider model-free algorithms with function approximation that learn value and advantage…

Machine Learning · Computer Science 2026-04-17 Wenlong Mou

In this work, we propose a class of numerical schemes for solving semilinear Hamilton-Jacobi-Bellman-Isaacs (HJBI) boundary value problems which arise naturally from exit time problems of diffusion processes with controlled drift. We…

Numerical Analysis · Mathematics 2020-02-14 Kazufumi Ito , Christoph Reisinger , Yufei Zhang

In this paper, we introduce Hamilton-Jacobi-Bellman (HJB) equations for Q-functions in continuous time optimal control problems with Lipschitz continuous controls. The standard Q-function used in reinforcement learning is shown to be the…

Optimization and Control · Mathematics 2020-05-05 Jeongho Kim , Insoon Yang