English
Related papers

Related papers: Thompson Sampling for Parameterized Markov Decisio…

200 papers

This work tackles the complexities of multi-player scenarios in \emph{unknown games}, where the primary challenge lies in navigating the uncertainty of the environment through bandit feedback alongside strategic decision-making. We…

Machine Learning · Computer Science 2024-02-27 Yingru Li , Liangqi Liu , Wenqiang Pu , Hao Liang , Zhi-Quan Luo

This paper shows that the optimal policy and value functions of a Markov Decision Process (MDP), either discounted or not, can be captured by a finite-horizon undiscounted Optimal Control Problem (OCP), even if based on an inexact model.…

Systems and Control · Electrical Eng. & Systems 2023-02-08 Arash Bahari Kordabad , Mario Zanon , Sebastien Gros

In this study, I investigate the dynamic decision problem with a finite parameter space when the functional form of conditional expected rewards is misspecified. Traditional algorithms, such as Thompson Sampling, guarantee neither an…

Econometrics · Economics 2025-05-22 Xinyu Dai

This paper proposes an observer-based framework for solving Partially Observable Markov Decision Processes (POMDPs) when an accurate model is not available. We first propose to use a Moving Horizon Estimation-Model Predictive Control…

Systems and Control · Electrical Eng. & Systems 2021-03-23 Hossein Nejatbakhsh Esfahani , Arash Bahari Kordabad , Sebastien Gros

We consider a planning problem where the dynamics and rewards of the environment depend on a hidden static parameter referred to as the context. The objective is to learn a strategy that maximizes the accumulated reward across all contexts.…

Machine Learning · Statistics 2015-02-10 Assaf Hallak , Dotan Di Castro , Shie Mannor

A labelled Markov decision process is a labelled Markov chain with nondeterminism, i.e., together with a strategy a labelled MDP induces a labelled Markov chain. The model is related to interval Markov chains. Motivated by applications of…

Formal Languages and Automata Theory · Computer Science 2020-09-25 Stefan Kiefer , Qiyi Tang

In stochastic bandit problems, a Bayesian policy called Thompson sampling (TS) has recently attracted much attention for its excellent empirical performance. However, the theoretical analysis of this policy is difficult and its asymptotic…

Statistics Theory · Mathematics 2013-11-11 Junya Honda , Akimichi Takemura

We present a new method for statistical verification of quantitative properties over a partially unknown system with actions, utilising a parameterised model (in this work, a parametric Markov decision process) and data collected from…

Machine Learning · Computer Science 2017-07-06 Elizabeth Polgreen , Viraj Wijesuriya , Sofie Haesaert , Alessandro Abate

We consider Markov decision processes (MDPs) with multiple limit-average (or mean-payoff) objectives. There exist two different views: (i) the expectation semantics, where the goal is to optimize the expected mean-payoff objective, and (ii)…

Logic in Computer Science · Computer Science 2019-03-14 Krishnendu Chatterjee , Zuzana Křetínská , Jan Křetínský

Constrained Markov Decision Processes (CMDPs) are notably more complex to solve than standard MDPs due to the absence of universally optimal policies across all initial state distributions. This necessitates re-solving the CMDP whenever the…

Machine Learning · Computer Science 2025-10-02 Alperen Tercan , Necmiye Ozay

Partially Observable Markov Decision Processes (POMDPs) are systems in which one agent interacts with a stochastic environment, and receives only partial information about the current state. In a multi-environment POMDP (MEPOMDP), the…

Artificial Intelligence · Computer Science 2026-05-11 Léonard Brice , Filip Cano , Krishnendu Chatterjee , Thomas A. Henzinger , Stefanie Muroya

We prove new upper and lower bounds for sample complexity of finding an $\epsilon$-optimal policy of an infinite-horizon average-reward Markov decision process (MDP) given access to a generative model. When the mixing time of the…

Machine Learning · Computer Science 2021-06-15 Yujia Jin , Aaron Sidford

Partially Observable Monte-Carlo Planning (POMCP) is a powerful online algorithm able to generate approximate policies for large Partially Observable Markov Decision Processes. The online nature of this method supports scalability by…

Artificial Intelligence · Computer Science 2021-04-29 Giulio Mazzi , Alberto Castellini , Alessandro Farinelli

We study and provide efficient algorithms for multi-objective model checking problems for Markov Decision Processes (MDPs). Given an MDP, M, and given multiple linear-time (\omega -regular or LTL) properties \varphi\_i, and probabilities…

Logic in Computer Science · Computer Science 2015-07-01 Kousha Etessami , Marta Kwiatkowska , Moshe Y. Vardi , Mihalis Yannakakis

General-purpose, intelligent, learning agents cycle through sequences of observations, actions, and rewards that are complex, uncertain, unknown, and non-Markovian. On the other hand, reinforcement learning is well-developed for small…

Machine Learning · Computer Science 2009-12-30 Marcus Hutter

Reinforcement learning would enjoy better success on real-world problems if domain knowledge could be imparted to the algorithm by the modelers. Most problems have both hidden state and unknown dynamics. Partially observable Markov decision…

Machine Learning · Computer Science 2013-01-07 Christian R. Shelton

We propose a Thompson sampling-based learning algorithm for the Linear Quadratic (LQ) control problem with unknown system parameters. The algorithm is called Thompson sampling with dynamic episodes (TSDE) where two stopping criteria…

Systems and Control · Computer Science 2017-09-14 Yi Ouyang , Mukul Gagrani , Rahul Jain

We develop a qualitative theory of Markov Decision Processes (MDPs) and Partially Observable MDPs that can be used to model sequential decision making tasks when only qualitative information is available. Our approach is based upon an…

Artificial Intelligence · Computer Science 2013-01-07 Blai Bonet , Judea Pearl

Contextual bandits constitute a classical framework for decision-making under uncertainty. In this setting, the goal is to learn the arms of highest reward subject to contextual information, while the unknown reward parameters of each arm…

Machine Learning · Statistics 2024-02-19 Hongju Park , Mohamad Kazem Shirani Faradonbeh

Here, we explore the problem of error propagation mitigation in modular digital twins as a sequential decision process. Building on a companion study that used a Hidden Markov Model (HMM) to infer latent error regimes from surrogate-physics…

Machine Learning · Computer Science 2026-04-27 Annice Najafi , Shokoufeh Mirzaei