Abstract
AbstractMarkov decision process (MDP) offers a general framework for modelling sequential decision making where outcomes are random. In particular, it serves as a mathematical framework for reinforcement learning. This paper introduces an extension of MDP, namely quantum MDP (qMDP), that can serve as a mathematical model of decision making about quantum systems. We develop dynamic programming algorithms for policy evaluation and finding optimal policies for qMDPs in the case of finite-horizon. The results obtained in this paper provide some useful mathematical tools for reinforcement learning techniques applied to the quantum world.
Publisher
Springer Science and Business Media LLC
Subject
Applied Mathematics,Computer Science Applications,Modeling and Simulation,Control and Systems Engineering
Reference28 articles.
1. M. L. Puterman. Markov Decision Processes: Discrete Stochastic Dynamic Programming, Hoboken, USA: John Wiley, 2005.
2. L. P. Kaelbling, M. L. Littman, A. R. Cassandra. Planning and acting in partially observable stochastic domains. Artificial Intelligence, vol. 101, no. 1–2, pp. 99–134, 1998. DOI: https://doi.org/10.1016/S0004-3702(98)00023-X.
3. J. Barry, D. T. Barry, S. Aaronson. Quantum partially observable Markov decision processes. Physical Review A, vol. 90, no. 3, Article number 032311, 2014. DOI: https://doi.org/10.1103/PhysRevA.90.032311.
4. S. G. Ying, M. S. Ying. Reachability analysis of quantum Markov decision processes. Information and Computation, vol. 263, pp. 31–51, 2018. DOI: https://doi.org/10.1016/j.ic.2018.09.001.
5. M. S. Ying. Foundations of Quantum Programming, Amsterdam, Netherlands: Morgan Kaufmann, 2016.
Cited by
9 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献