English
Related papers

Related papers: Policy Gradient for Continuous-Time Mean-Field Con…

200 papers

Following Kolokoltsov's work [1], we present an extension of mean-field control theory in quantum framework. In particular such an extension is done naturally by considering the Belavkin quantum filtering and control theory in a mean-field…

Optimization and Control · Mathematics 2023-06-27 Sofiane Chalal , Nina H. Amini , Gaoyue Guo

We consider policy gradient methods for stochastic optimal control problem in continuous time. In particular, we analyze the gradient flow for the control, viewed as a continuous time limit of the policy gradient method. We prove the global…

Optimization and Control · Mathematics 2025-04-15 Mo Zhou , Jianfeng Lu

In this paper, we study a class of discrete-time mean-field games under the infinite-horizon risk-sensitive discounted-cost optimality criterion. Risk-sensitivity is introduced for each agent (player) via an exponential utility function. In…

Optimization and Control · Mathematics 2018-10-08 Naci Saldi , Tamer Basar , Maxim Raginsky

Variational methods have been used to study stochastic control for long, see Bensoussan (1982) and Bensoussan-Lions (1978) for the early works. More precisely, variational approaches apply to the study of Bellman equation as a parabolic…

Optimization and Control · Mathematics 2025-12-01 Alain Bensoussan , Ziyu Huang , Sheung Chi Phillip Yam

We consider the stochastic optimal control problem of nonlinear mean-field systems in discrete time. We reformulate the problem into a deterministic control problem with marginal distribution as controlled state variable, and prove that…

Probability · Mathematics 2015-12-01 Huyên Pham , Xiaoli Wei

We prove the stability and global convergence of a coupled actor-critic gradient flow for infinite-horizon and entropy-regularised Markov decision processes (MDPs) in continuous state and action space with linear function approximation…

Optimization and Control · Mathematics 2025-10-17 Denis Zorba , David Šiška , Lukasz Szpruch

Markov reward processes (MRPs) are used to model stochastic phenomena arising in operations research, control engineering, robotics, and artificial intelligence, as well as communication and transportation networks. In many of these cases,…

Machine Learning · Statistics 2020-09-17 Ashwin Pananjady , Martin J. Wainwright

We consider policy evaluation in infinite-horizon discounted Markov decision problems (MDPs) with infinite spaces. We reformulate this task a compositional stochastic program with a function-valued decision variable that belongs to a…

Optimization and Control · Mathematics 2020-05-19 Alec Koppel , Garrett Warnell , Ethan Stump , Peter Stone , Alejandro Ribeiro

In this paper, we propose a new policy iteration algorithm to compute the value function and the optimal controls of continuous time stochastic control problems. The algorithm relies on successive approximations using linear-quadratic…

Optimization and Control · Mathematics 2024-09-09 Dylan Possamaï , Ludovic Tangpi

Off-policy learning refers to the problem of learning the value function of a way of behaving, or policy, while following a different policy. Gradient-based off-policy learning algorithms, such as GTD and TDC/GQ, converge even when using…

Artificial Intelligence · Computer Science 2015-12-15 Lucas Lehnert , Doina Precup

Reinforcement learning methods for robotics are increasingly successful due to the constant development of better policy gradient techniques. A precise (low variance) and accurate (low bias) gradient estimator is crucial to face…

Machine Learning · Computer Science 2021-07-21 João Carvalho , Davide Tateo , Fabio Muratore , Jan Peters

We propose a comprehensive framework for policy gradient methods tailored to continuous time reinforcement learning. This is based on the connection between stochastic control problems and randomised problems, enabling applications across…

Optimization and Control · Mathematics 2024-05-01 Robert Denkert , Huyên Pham , Xavier Warin

Standard formulations of prescribed worst-case disturbance energy-gain control policies for linear time-varying systems depend on all forward model data. In discrete time, this dependence arises through a backward Riccati recursion. This…

Optimization and Control · Mathematics 2026-05-22 Jintao Sun , Michael Cantoni

We develop policy gradients methods for stochastic control with exit time in a model-free setting. We propose two types of algorithms for learning either directly the optimal policy or by learning alternately the value function (critic) and…

Computational Finance · Quantitative Finance 2023-02-16 Mohamed Hamdouche , Pierre Henry-Labordere , Huyen Pham

We study the policy gradient method (PGM) for the linear quadratic Gaussian (LQG) dynamic output-feedback control problem using an input-output-history (IOH) representation of the closed-loop system. First, we show that any dynamic…

Optimization and Control · Mathematics 2025-10-23 Tomonori Sadamoto , Takashi Tanaka

This paper studies the continuous-time q-learning in mean-field jump-diffusion models when the population distribution is not directly observable. We propose the integrated q-function in decoupled form (decoupled Iq-function) from the…

Optimization and Control · Mathematics 2025-03-24 Xiaoli Wei , Xiang Yu , Fengyi Yuan

Policy gradient algorithms typically combine discounted future rewards with an estimated value function, to compute the direction and magnitude of parameter updates. However, for most Reinforcement Learning tasks, humans can provide…

Machine Learning · Computer Science 2019-04-09 Ishan Durugkar , Matthew Hausknecht , Adith Swaminathan , Patrick MacAlpine

Policy gradient methods in reinforcement learning update policy parameters by taking steps in the direction of an estimated gradient of policy value. In this paper, we consider the statistically efficient estimation of policy gradients from…

Machine Learning · Statistics 2020-02-21 Nathan Kallus , Masatoshi Uehara

Policy gradient is a generic and flexible reinforcement learning approach that generally enjoys simplicity in analysis, implementation, and deployment. In the last few decades, this approach has been extensively advanced for fully…

Machine Learning · Computer Science 2020-05-26 Kamyar Azizzadenesheli , Yisong Yue , Animashree Anandkumar

The classical policy gradient method is the theoretical and conceptual foundation of modern policy-based reinforcement learning (RL) algorithms. Most rigorous analyses of such methods, particularly those establishing convergence guarantees,…

Machine Learning · Computer Science 2026-02-11 Jongmin Lee , Ernest K. Ryu