English

A note on the article "On Exploiting Spectral Properties for Solving MDP with Large State Space"

Machine Learning 2021-07-20 v1 Optimization and Control
Authors: D. Maran
View on arXiv ↗ PDF ↗

Abstract

We improve a theoretical result of the article "On Exploiting Spectral Properties for Solving MDP with Large State Space" showing that their algorithm, which was proved to converge under some unrealistic assumptions, is actually guaranteed to converge always.

Cite

@article{arxiv.2107.08488,
  title  = {A note on the article "On Exploiting Spectral Properties for Solving MDP with Large State Space"},
  author = {D. Maran},
  journal= {arXiv preprint arXiv:2107.08488},
  year   = {2021}
}

Related papers

View all related →
Numerical Analysis · Mathematics
On The Convergence of the Discretized Linear Static State-Based Peridynamic Equations
Lukas Pflug, Michael Stingl, Max Zetzmann
2026-03-04
Probability · Mathematics
Convergence Rates of Attractive-Repulsive MCMC Algorithms
Yu Hang Jiang, Tong Liu, Zhiya Lou, Jeffrey S. Rosenthal +3
2021-09-03
Machine Learning · Computer Science
Solving Continual Combinatorial Selection via Deep Reinforcement Learning
Hyungseok Song, Hyeryung Jang, Hai H. Tran, Se-eun Yoon +4
2019-09-10
Machine Learning · Computer Science
On Value Iteration Convergence in Connected MDPs
Arsenii Mustafin, Alex Olshevsky, Ioannis Ch. Paschalidis
2024-06-17
Systems and Control · Electrical Eng. & Systems
Anytime Guarantees for Reachability in Uncountable Markov Decision Processes
Kush Grover, Jan Křetínský, Tobias Meggendorfer, Maximilian Weininger
2022-07-13
Machine Learning · Computer Science
MDP Geometry, Normalization and Reward Balancing Solvers
Arsenii Mustafin, Aleksei Pakharev, Alex Olshevsky, Ioannis Ch. Paschalidis
2025-03-06
Multiagent Systems · Computer Science
Scalable spectral representations for multi-agent reinforcement learning in network MDPs
Zhaolin Ren, Runyu Zhang, Bo Dai, Na Li
2024-11-19
Logic in Computer Science · Computer Science
The Value Problem for Multiple-Environment MDPs with Parity Objective
Krishnendu Chatterjee, Laurent Doyen, Jean-François Raskin, Ocan Sankur
2025-04-23
Artificial Intelligence · Computer Science
Improved Memory-Bounded Dynamic Programming for Decentralized POMDPs
Sven Seuken, Shlomo Zilberstein
2012-06-26
Artificial Intelligence · Computer Science
Bounded Optimal Exploration in MDP
Kenji Kawaguchi
2016-04-06
Information Theory · Computer Science
Achieving Super-Resolution in Multi-Rate Sampling Systems via Efficient Semidefinite Programming
M. Ferreira Da Costa, W. Dai
2016-11-24
Optimization and Control · Mathematics
Robust Quadratic Programming with Mixed-Integer Uncertainty
Areesh Mittal, Can Gokalp, Grani A. Hanasusanto
2018-12-19
Formal Languages and Automata Theory · Computer Science
Probabilistic Bisimulations for PCTL Model Checking of Interval MDPs
Vahid Hashemi, Hassan Hatefi, Jan Krčál
2014-04-11
Logic in Computer Science · Computer Science
Tractable Hyperproperties for MDPs
Lina Gerlach, Tobias Winkler, Erika Ábrahám, Borzoo Bonakdarpour +1
2026-04-09
Machine Learning · Computer Science
A Convergence Result for Regularized Actor-Critic Methods
Wesley Suttle, Zhuoran Yang, Kaiqing Zhang, Ji Liu
2019-10-23
Artificial Intelligence · Computer Science
Solving POMDPs by Searching the Space of Finite Policies
Nicolas Meuleau, Kee-Eung Kim, Leslie Pack Kaelbling, Anthony R. Cassandra
2013-01-30
Machine Learning · Computer Science
On the Practical Consistency of Meta-Reinforcement Learning Algorithms
Zheng Xiong, Luisa Zintgraf, Jacob Beck, Risto Vuorio +1
2021-12-02
Optimization and Control · Mathematics
Approximate Constrained Discounted Dynamic Programming with Uniform Feasibility and Optimality
Hyeong Soo Chang
2023-08-08
Machine Learning · Computer Science
An Adaptive State Aggregation Algorithm for Markov Decision Processes
Guanting Chen, Johann Demetrio Gaebler, Matt Peng, Chunlin Sun +1
2021-07-26
Dynamical Systems · Mathematics
Spectral methods for limit theorems for random expanding transformations
Yeor Hafouta
2024-08-14
Optimization and Control · Mathematics
Large-Scale Markov Decision Problems via the Linear Programming Dual
Yasin Abbasi-Yadkori, Peter L. Bartlett, Xi Chen, Alan Malek
2019-01-09
Artificial Intelligence · Computer Science
Efficient Solution Algorithms for Factored MDPs
C. Guestrin, D. Koller, R. Parr, S. Venkataraman
2011-06-10
Machine Learning · Computer Science
Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation
Aivar Sootla, Alexander I. Cowen-Rivers, Taher Jafferjee, Ziyan Wang +3
2022-06-23
Methodology · Statistics
A Stable Manifold MCMC Method for High Dimensions
Alexandros Beskos
2014-04-01
Functional Analysis · Mathematics
Fixed point problems in Banach spaces
Abba Auwalu
2015-08-28
R2 v1 2026-06-24T04:17:58.184Z