A Computational Model of Learning from Replayed Experience in Spatial NavigationReport as inadecuate




A Computational Model of Learning from Replayed Experience in Spatial Navigation - Download this document for free, or read online. Document in PDF available to download.

Experience replay, Reinforcement learning, Spatial navigation

Mirian HosseinAbadi, MahdiehSadat

Supervisor and department: Sutton, Rich Computing Science Elio, Renee Computing Science

Examining committee member and department: Schuurmans, Dale Computing Science Spetch, Marcia Psychology Ludvig, Elliot Princeton Neuroscience Institute, Princeton University

Department: Department of Computing Science

Specialization:

Date accepted: 2011-11-28T21:53:49Z

Graduation date: 2012-06

Degree: Master of Science

Degree level: Master's

Abstract: In this thesis we propose a computational model of animal behavior in spatial navigation, based on reinforcement learning ideas. In the field of computer science and specifically artificial intelligence, replay refers to retrieving and reprocessing the experiences that are stored in an abstract representation of the environment. Our model uses the replay idea that existed separately in both computer science and neuroscience. In neuroscience, it refers to the reactivation of neurons in the hippocampus that were previously active during a learning task, in such a way that can be interpreted as replaying previous experiences. Therefore, it is natural to use RL algorithms to model the biological replay phenomena.We illustrated, through computational experiments, that our replay model can explain many previously hard-to-explain behavioral navigational experiments such as latent learning or insight experiments. There have been many computational models proposed to model rats behavior in mazes or open field environments. We showed that our model has two major advantages over prior ones: i The learning algorithm used in our model is simpler than that of previous computational models, yet capable of explaining complicated behavioral phenomena in spatial navigation. ii our model generates different replay sequences that are consistent with replay patterns observed in the neural experiments on the rat brain.

Language: English

DOI: doi:10.7939-R3MD8M

Rights: License granted by MahdiehSadat Mirian HosseinAbadi mirianho@ualberta.ca on 2011-11-28T12:01:48Z GMT: Permission is hereby granted to the University of Alberta Libraries to reproduce single copies of this thesis and to lend or sell such copies for private, scholarly or scientific research purposes only. Where the thesis is converted to, or otherwise made available in digital form, the University of Alberta will advise potential users of the thesis of the above terms. The author reserves all other publication and other rights in association with the copyright in the thesis, and except as herein provided, neither the thesis nor any substantial portion thereof may be printed or otherwise reproduced in any material form whatsoever without the author's prior written permission.





Author: Mirian HosseinAbadi, MahdiehSadat

Source: https://era.library.ualberta.ca/


Teaser



Imagination is more important than knowledge.
For knowledge is limited, whereas imagination embraces the entire world, stimulating progress, giving birth to evolution. – Albert Einstein, 1931. University of Alberta A C OMPUTATIONAL M ODEL OF L EARNING FROM R EPLAYED E XPERIENCE IN S PATIAL NAVIGATION by MahdiehSadat Mirian HosseinAbadi A thesis submitted to the Faculty of Graduate Studies and Research in partial fulfillment of the requirements for the degree of Master of Science Department of Computing Science c ⃝MahdiehSadat Mirian HosseinAbadi Spring 2012 Edmonton, Alberta Permission is hereby granted to the University of Alberta Libraries to reproduce single copies of this thesis and to lend or sell such copies for private, scholarly or scientific research purposes only. Where the thesis is converted to, or otherwise made available in digital form, the University of Alberta will advise potential users of the thesis of these terms. The author reserves all other publication and other rights in association with the copyright in the thesis, and except as herein before provided, neither the thesis nor any substantial portion thereof may be printed or otherwise reproduced in any material form whatever without the author’s prior written permission. To my beloved parents Abstract In this thesis we propose a computational model of animal behavior in spatial navigation, based on reinforcement learning ideas.
In the field of computer science and specifically artificial intelligence, replay refers to retrieving and reprocessing the experiences that are stored in an abstract representation of the environment.
Our model uses the replay idea that existed separately in both computer science and neuroscience.
In neuroscience, it refers to the reactivation of neurons in the hippocampus that were previously active during a learning task, in such a way that can be interpreted as replaying previous experiences.
Therefore, it is natural to use RL algorithms to mode...





Related documents