English
Related papers

Related papers: Mean field for Markov Decision Processes: from Dis…

200 papers

We study the time-bounded reachability problem for continuous-time Markov decision processes (CTMDPs) and games (CTMGs). Existing techniques for this problem use discretisation techniques to break time into discrete intervals, and optimal…

Computer Science and Game Theory · Computer Science 2011-07-11 John Fearnley , Markus Rabe , Sven Schewe , Lijun Zhang

This paper studies the risk-averse mean-variance optimization in infinite-horizon discounted Markov decision processes (MDPs). The involved variance metric concerns reward variability during the whole process, and future deviations are…

Optimization and Control · Mathematics 2022-01-19 Shuai Ma , Xiaoteng Ma , Li Xia

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

In this article we study a finite horizon optimal control problem with monotone controls. We consider the associated Hamilton-Jacobi-Bellman (HJB) equation which characterizes the value function. We consider the totally discretized problem…

Optimization and Control · Mathematics 2014-07-08 Eduardo A. Philipp , Laura S. Aragone , Lisandro A. Parente

Markov decision processes (MDPs) are a popular model for performance analysis and optimization of stochastic systems. The parameters of stochastic behavior of MDPs are estimates from empirical observations of a system; their values are not…

Artificial Intelligence · Computer Science 2017-10-26 Dimitri Scheftelowitsch , Peter Buchholz , Vahid Hashemi , Holger Hermanns

The Markov assumption in Markov Decision Processes (MDPs) is fundamental in reinforcement learning, influencing both theoretical research and practical applications. Existing methods that rely on the Bellman equation benefit tremendously…

Methodology · Statistics 2024-09-24 Chuyun Ye , Lixing Zhu , Ruoqing Zhu

We present the first finite time global convergence analysis of policy gradient in the context of infinite horizon average reward Markov decision processes (MDPs). Specifically, we focus on ergodic tabular MDPs with finite state and action…

Machine Learning · Computer Science 2024-03-12 Navdeep Kumar , Yashaswini Murthy , Itai Shufaro , Kfir Y. Levy , R. Srikant , Shie Mannor

The statement of the mean field approximation theorem in the mean field theory of Markov processes particularly targets the behaviour of population processes with an unbounded number of agents. However, in most real-world engineering…

Probability · Mathematics 2017-05-11 Mahmoud Talebi , Jan Friso Groote , Jean-Paul Linnartz

Markov decision processes (MDPs) are standard models for probabilistic systems with non-deterministic behaviours. Mean payoff (or long-run average reward) provides a mathematically elegant formalism to express performance related…

Performance · Computer Science 2017-09-08 Jan Křetínský , Tobias Meggendorfer

We study Markov decision processes (MDPs) with multiple limit-average (or mean-payoff) functions. We consider two different objectives, namely, expectation and satisfaction objectives. Given an MDP with k limit-average functions, in the…

Computer Science and Game Theory · Computer Science 2015-07-01 Tomáš Brázdil , Václav Brožek , Krishnendu Chatterjee , Vojtěch Forejt , Antonín Kučera

This paper proposes a computationally tractable algorithm for learning infinite-horizon average-reward linear mixture Markov decision processes (MDPs) under the Bellman optimality condition. Our algorithm for linear mixture MDPs achieves a…

Machine Learning · Computer Science 2024-10-22 Woojin Chae , Kihyuk Hong , Yufan Zhang , Ambuj Tewari , Dabeen Lee

In this report we derive the strategic (deterministic) allocation to bonds and stocks resulting in the optimal mean-variance trade-off on a given investment horizon. The underlying capital market features a mean-reverting process for equity…

Mathematical Finance · Quantitative Finance 2022-01-17 Søren Fiig Jarner

This paper studies the time-inconsistent MV optimal stopping problem via a game-theoretic approach to find equilibrium strategies. To overcome the mathematical intractability of direct equilibrium analysis, we propose a vanishing…

Optimization and Control · Mathematics 2025-10-29 Yuchao Dong , Harry Zheng

This study presents a robust optimization algorithm for automated highway merge. The merging scenario is one of the challenging scenes in automated driving, because it requires adjusting ego vehicle's speed to match other vehicles before…

Robotics · Computer Science 2025-03-20 Takeru Goto , Kosuke Toda , Takayasu Kumano

We consider the batch (off-line) policy learning problem in the infinite horizon Markov Decision Process. Motivated by mobile health applications, we focus on learning a policy that maximizes the long-term average reward. We propose a…

Statistics Theory · Mathematics 2022-09-20 Peng Liao , Zhengling Qi , Runzhe Wan , Predrag Klasnja , Susan Murphy

This paper considers consumption and portfolio optimization problems with recursive preferences in both infinite and finite time regions. Specially, the financial market consists of a risk-free asset and a risky asset that follows a general…

Optimization and Control · Mathematics 2024-12-30 Jian-hao Kang , Zhun Gou , Nan-jing Huang

We investigate reinforcement learning in the setting of Markov decision processes for a large number of exchangeable agents interacting in a mean field manner. Applications include, for example, the control of a large number of robots…

Optimization and Control · Mathematics 2025-04-30 René Carmona , Mathieu Laurière , Zongjun Tan

Consensus based optimization (CBO) employs a swarm of particles evolving as a system of stochastic differential equations (SDEs). Recently, it has been adapted to yield a derivative free sampling method referred to as consensus based…

Optimization and Control · Mathematics 2024-09-06 Marvin Koß , Simon Weissmann , Jakob Zech

This paper first describes a class of uncertain stochastic control systems with Markovian switching, and derives an It\^o-Liu formula for Markov-modulated processes. And we characterize an optimal control law, which satisfies the…

Optimization and Control · Mathematics 2014-01-14 Weiyin Fei

We formally verify executable algorithms for solving Markov decision processes (MDPs) in the interactive theorem prover Isabelle/HOL. We build on existing formalizations of probability theory to analyze the expected total reward criterion…

Artificial Intelligence · Computer Science 2023-03-09 Maximilian Schäfeller , Mohammad Abdulaziz