English
Related papers

Related papers: Memory-Limited Partially Observable Stochastic Con…

200 papers

It is well known that for any finite state Markov decision process (MDP) there is a memoryless deterministic policy that maximizes the expected reward. For partially observable Markov decision processes (POMDPs), optimal memoryless policies…

Optimization and Control · Mathematics 2016-02-16 Guido Montufar , Keyan Ghazi-Zahedi , Nihat Ay

We consider the problem of finding the best memoryless stochastic policy for an infinite-horizon partially observable Markov decision process (POMDP) with finite state and action spaces with respect to either the discounted or mean reward…

Optimization and Control · Mathematics 2022-05-02 Johannes Müller , Guido Montúfar

In this paper, we first prove that the mean-field stochastic linear quadratic (MFSLQ for short) control problem with random coefficients has a unique optimal control and derive a preliminary stochastic maximum principle to characterize this…

Optimization and Control · Mathematics 2025-05-28 Jie Xiong , Wen Xu

We consider optimal signalling and control of discrete-time nonlinear partially observable stochastic systems in state space form. In the first part of the paper, we characterize the operational {\it control-coding capacity}, $C_{FB}$ in…

Information Theory · Computer Science 2024-07-29 Charalambos D. Charalambous , Stelios Louka

In this paper we are interested in a new type of {\it mean-field}, non-Markovian stochastic control problems with partial observations. More precisely, we assume that the coefficients of the controlled dynamics depend not only on the paths…

Probability · Mathematics 2017-02-21 Rainer Buckdahn , Juan Li , Jin Ma

This work puts forward a novel numerical approach for solving the stochastic optimal control problem (SOCP) and the mean field control (MFC) problem using projection algorithm inspired by the stochastic maximum principle (SMP) which is also…

Optimization and Control · Mathematics 2026-04-09 Hui Sun

We study provable multi-agent reinforcement learning (RL) in the general framework of partially observable stochastic games (POSGs). To circumvent the known hardness results and the use of computationally intractable oracles, we advocate…

Machine Learning · Computer Science 2026-03-16 Xiangyu Liu , Kaiqing Zhang

We propose a simple and original approach for solving linear-quadratic mean-field stochastic control problems. We study both finite-horizon and infinite-horizon pro\-blems, and allow notably some coefficients to be stochastic. Extension to…

Probability · Mathematics 2018-10-26 Matteo Basei , Huyên Pham

This paper is concerned with mean-field stochastic linear-quadratic (MF-SLQ, for short) optimal control problems with deterministic coefficients. The notion of weak closed-loop optimal strategy is introduced. It is shown that the open-loop…

Optimization and Control · Mathematics 2019-09-27 Jingrui Sun , Hanxiao Wang

A number of optimal decision problems with uncertainty can be formulated into a stochastic optimal control framework. The Least-Squares Monte Carlo (LSMC) algorithm is a popular numerical method to approach solutions of such stochastic…

Computational Finance · Quantitative Finance 2019-01-23 Zhiyi Shen , Chengguo Weng

We present a memory-bounded optimization approach for solving infinite-horizon decentralized POMDPs. Policies for each agent are represented by stochastic finite state controllers. We formulate the problem of optimizing these policies as a…

Artificial Intelligence · Computer Science 2012-06-26 Christopher Amato , Daniel S Bernstein , Shlomo Zilberstein

This paper focuses on indefinite stochastic mean-field linear-quadratic (MF-LQ, for short) optimal control problems, which allow the weighting matrices for state and control in the cost functional to be indefinite. The solvability of…

Optimization and Control · Mathematics 2020-12-02 Na Li , Xun Li , Zhiyong Yu

Perception-related tasks often arise in autonomous systems operating under partial observability. This work studies the problem of synthesizing optimal policies for complex perception-related objectives in environments modeled by partially…

Systems and Control · Electrical Eng. & Systems 2025-07-08 Zetong Xuan , Yu Wang

This paper studies the partially observed stochastic optimal control problem for systems with state dynamics governed by partial differential equations (PDEs) that leads to an extremely large problem. First, an open-loop deterministic…

Optimization and Control · Mathematics 2017-11-06 Dan Yu , Mohammadhussein Rafieisakhaei , Suman Chakravorty

Autonomous systems often have logical constraints arising, for example, from safety, operational, or regulatory requirements. Such constraints can be expressed using temporal logic specifications. The system state is often partially…

Artificial Intelligence · Computer Science 2024-06-21 Krishna C. Kalagarla , Dhruva Kartik , Dongming Shen , Rahul Jain , Ashutosh Nayyar , Pierluigi Nuzzo

Model predictive control (MPC) is a powerful control method that handles dynamical systems with constraints. However, solving MPC iteratively in real time, i.e., implicit MPC, remains a computational challenge. To address this, common…

Systems and Control · Electrical Eng. & Systems 2022-08-03 Fangyu Wu , Guanhua Wang , Siyuan Zhuang , Kehan Wang , Alexander Keimer , Ion Stoica , Alexandre Bayen

A general model of decentralized stochastic control called partial history sharing information structure is presented. In this model, at each step the controllers share part of their observation and control history with each other. This…

Systems and Control · Computer Science 2012-09-11 Ashutosh Nayyar , Aditya Mahajan , Demosthenis Teneketzis

This paper first presents necessary and sufficient conditions for the solvability of discrete time, mean-field, stochastic linear-quadratic optimal control problems. Then, by introducing several sequences of bounded linear operators, the…

Optimization and Control · Mathematics 2016-07-25 Robert. J Elliott , Xun Li , Yuan-Hua Ni

The synthesis problem for partially observable Markov decision processes (POMDPs) is to compute a policy that satisfies a given specification. Such policies have to take the full execution history of a POMDP into account, rendering the…

Artificial Intelligence · Computer Science 2020-07-20 Leonore Winterer , Ralf Wimmer , Nils Jansen , Bernd Becker

In this paper, we address the problem of stochastic motion planning under partial observability, more specifically, how to navigate a mobile robot equipped with continuous range sensors such as LIDAR. In contrast to many existing robotic…

Robotics · Computer Science 2020-12-03 Ke Sun , Brent Schlotfeldt , George Pappas , Vijay Kumar