Offline and Online Time in Sequential Decision-Making Problems

Aman Soni, Peter R. Lewis and Aniko Ekart
A. Soni, P. R. Lewis and A. Ekárt, "Offline and online time in Sequential Decision-Making Problems," Proceedings of the 2016 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1-8. 2016

A connection has recently been drawn between Dynamic Optimization Problems (DOPs) and Reinforcement Learning Problems (RLPs) where they can be seen as subsets of a broader class of Sequential Decision-Making Problems (SDMPs). SDMPs require new decisions on an ongoing basis. Typically the underlying environment changes between decisions. The SDMP view is useful as it allows the unified space to be explored. Solutions can be designed for characteristics of problem instances using algorithms from either community. Little has been done on comparing algorithm performance across these communities, particularly under real-world resource constraints.

@INPROCEEDINGS{7849961,
author={A. Soni and P. R. Lewis and A. Ekárt},
booktitle={2016 IEEE Symposium Series on Computational Intelligence (SSCI)},
title={Offline and online time in Sequential Decision-Making Problems},
year={2016},
pages={1-8},
keywords={Algorithm design and analysis;Benchmark testing;Decision making;Games;Heuristic algorithms;Learning (artificial intelligence);Optimization},
doi={10.1109/SSCI.2016.7849961},
month={Dec},}