paper-with-me

Papers

Bayesian Learning of Optimal Policies in Markov Decision Processes with Countably Infinite State-Space

2023-06-05 · NeurIPS 2023 11 · Saghar Adler, Vijay Subramanian

Models of many real-life applications, such as queuing models of communication networks or computing systems, have a countably infinite state-space. Algorithmic and learning procedures that have been developed to produce optimal policies mainly focus on finite state settings, and do not directly apply to these models. To overcome this lacuna, in this work we study the problem of optimal control of a family of discrete-time countable state-space Markov Decision Processes (MDPs) governed by an unknown parameter $\theta\in\Theta$, and defined on a countably-infinite state space $\mathcal X=\mathbb{Z}_+^d$, with finite action space $\mathcal A$, and an unbounded cost function. We take a Bayesian perspective with the random unknown parameter $\boldsymbol{\theta}^*$ generated via a given fixed prior distribution on $\Theta$. To optimally control the unknown MDP, we propose an algorithm based on Thompson sampling with dynamically-sized episodes: at the beginning of each episode, the posterior distribution formed via Bayes' rule is used to produce a parameter estimate, which then decides the policy applied during the episode. To ensure the stability of the Markov chain obtained by following the policy chosen for each parameter, we impose ergodicity assumptions. From this condition and using the solution of the average cost Bellman equation, we establish an $\tilde O(dh^d\sqrt{|\mathcal A|T})$ upper bound on the Bayesian regret of our algorithm, where $T$ is the time-horizon. Finally, to elucidate the applicability of our algorithm, we consider two different queuing models with unknown dynamics, and show that our algorithm can be applied to develop approximately optimal control algorithms.

📄 PDF Abstract BibTeX arXiv:2306.02574

Code (0)

등록된 구현이 없습니다.

Tasks

Thompson Sampling

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Bayesian regularization of empirical MDPs

2022-08-03 · Samarth Gupta, Daniel N. Hill, Lexing Ying, Inderjit Dhillon

In most applications of model-based Markov decision processes, the parameters for the unknown underlying model are often estimated from the empirical data. Due to noise, the policy learnedfrom the estimated model is ofte…

Optimal Inspection and Maintenance Planning for Deteriorating Structural Components through Dynamic Bayesian Networks and Markov Decision Processes

2020-09-09 · P. G. Morato, K. G. Papakonstantinou, C. P. Andriotis, J. S. Nielsen 외

Civil and maritime engineering systems, among others, from bridges to offshore platforms and wind turbines, must be efficiently managed as they are exposed to deterioration mechanisms throughout their operational life, s…

Decision MakingSequential Decision Making

Optimal Decision Tree Policies for Markov Decision Processes

2023-01-30 · Daniël Vos, Sicco Verwer

Interpretability of reinforcement learning policies is essential for many real-world tasks but learning such interpretable policies is a hard problem. Particularly rule-based policies such as decision trees and rules lis…

Imitation Learning

On the Use of Non-Stationary Policies for Stationary Infinite-Horizon Markov Decision Processes

2012-12-01 · NeurIPS 2012 12 · Bruno Scherrer, Boris Lesner

We consider infinite-horizon stationary $\gamma$-discounted Markov Decision Processes, for which it is known that there exists a stationary optimal policy. Using Value and Policy Iteration with some error $\epsilon…

An Efficient Solution to s-Rectangular Robust Markov Decision Processes

2023-01-31 · Navdeep Kumar, Kfir Levy, Kaixin Wang, Shie Mannor

We present an efficient robust value iteration for \texttt{s}-rectangular robust Markov Decision Processes (MDPs) with a time complexity comparable to standard (non-robust) MDPs which is significantly faster than any exi…

LEMMA