@inproceedings{b2cefccf1614476a9ce9b3905ee3fcb9,
title = "An approximate stochastic annealing algorithm for finite horizon Markov decision processes",
abstract = "We present a simulation-based algorithm called Approximate Stochastic Annealing (ASA) for solving finitehorizon Markov decision processes (MDPs). The algorithm iteratively estimates the optimal policy by sampling from a sequence of probability distribution functions over the policy space. By exploiting a novel connection of ASA to the stochastic approximation method, we show that the sequence of distribution functions generated by the algorithm converges to a degenerated distribution that concentrates only on the optimal policy. Numerical examples are also provided to illustrate the algorithm.",
author = "Jiaqiao Hu and Chang, \{Hyeong Soo\}",
year = "2010",
doi = "10.1109/CDC.2010.5717689",
language = "English",
isbn = "9781424477456",
series = "Proceedings of the IEEE Conference on Decision and Control",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "5338--5343",
booktitle = "2010 49th IEEE Conference on Decision and Control, CDC 2010",
note = "49th IEEE Conference on Decision and Control, CDC 2010 ; Conference date: 15-12-2010 Through 17-12-2010",
}