Lucas, Simon M (2008) Investigating learning rates for evolution and temporal difference learning. In: 2008 IEEE Symposium On Computational Intelligence and Games (CIG), 2008-12-15 - 2008-12-18.
Lucas, Simon M (2008) Investigating learning rates for evolution and temporal difference learning. In: 2008 IEEE Symposium On Computational Intelligence and Games (CIG), 2008-12-15 - 2008-12-18.
Lucas, Simon M (2008) Investigating learning rates for evolution and temporal difference learning. In: 2008 IEEE Symposium On Computational Intelligence and Games (CIG), 2008-12-15 - 2008-12-18.
Abstract
Evidently, any learning algorithm can only learn on the basis of the information given to it. This paper presents a first attempt to place an upper bound on the information rates attainable with standard co-evolution and with TDL. The upper bound for TDL is shown to be much higher than for coevolution. Under commonly used settings for learning to play Othello for example, TDL may have an upper bound that is hundreds or even thousands of times higher than that of coevolution. To test how well these bounds correlate with actual learning rates, a simple two-player game called Treasure Hunt. is developed. While the upper bounds cannot be used to predict the number of games required to learn the optimal policy, they do correctly predict the rank order of the number of games required by each algorithm. © 2008 IEEE.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Additional Information: | Published proceedings: 2008 IEEE Symposium on Computational Intelligence and Games, CIG 2008 |
Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
Divisions: | Faculty of Science and Health Faculty of Science and Health > Computer Science and Electronic Engineering, School of |
SWORD Depositor: | Unnamed user with email elements@essex.ac.uk |
Depositing User: | Unnamed user with email elements@essex.ac.uk |
Date Deposited: | 03 Oct 2012 09:19 |
Last Modified: | 05 Dec 2024 19:32 |
URI: | http://repository.essex.ac.uk/id/eprint/4017 |
Available files
Filename: ciginfo.pdf