Sequential Decision-Making with Big Data
Papers from the 2014 AAAI Workshop
Amir-massoud Farahmand, André M.S. Barreto, Mohammad Ghavamzadeh, Joelle Pineau, Doina Precup, Workshop Organizers
Technical Report WS-14-12
40 pp.
Electronic Version of the Technical Report (Download only): $10.00 (Special Introductory Price)
Softcover version of the technical report: $25.00 softcover
(For international orders please shipping options before ordering on website.)
ISBN 978-1-57735-673-8
This workshop is about decision-making in the era of big data. The main topic of the workshop is complex decision-making problems, in particular the sequential ones, that arise in this context. Examples of these problems are high-dimensional large-scale reinforcement learning and their simplified version such as various types of bandit problems. These problems can be classified into three potentially overlapping categories: (1) Very large number of data-points. Examples: data coming from user clicks on the web and financial data. In this scenario, the most important issue is computational cost. Any algorithm that is super-linear will not be practical. (2) Very high-dimensional input space. Examples are found in robotic and computer vision problems. The only possible way to solve these problems is to benefit from their regularities. (3) Partially observable systems. Here the immediate observed variables do not have enough information for accurate decision-making, but one might extract sufficient information by considering the history of observations.