Exploring the Effect of Different Numbers of Convolutional Filters and Training Loops on the Performance of AlphaZero
In this work, the algorithm used by AlphaZero is adapted for dots and boxes, a two-player game. This algorithm is explored using different numbers of convolutional filters and training loops, in order to better understand the effect these parameters have on the learning of the player. Different boar...
Main Author: | Prince, Jared |
---|---|
Format: | Others |
Published: |
TopSCHOLAR®
2018
|
Subjects: | |
Online Access: | https://digitalcommons.wku.edu/theses/3087 https://digitalcommons.wku.edu/cgi/viewcontent.cgi?article=4090&context=theses |
Similar Items
-
Improving Monte Carlo Tree Search with Artificial Neural Networks without Heuristics
by: Alba Cotarelo, et al.
Published: (2021-02-01) -
AlphaZero with Input Convex Neural Networks
by: Zhang, Shuyuan
Published: (2020) -
Playing the Game of Risk with an AlphaZero Agent
by: Blomqvist, Erik
Published: (2020) -
A Software Framework for AlphaZero-Like Applications
by: Li, Wei, et al.
Published: (2018) -
PARALLEL MACHINE SCHEDULING WITH MONTE CARLO TREE SEARCH
by: Anita Agárdi, et al.
Published: (2021-04-01)