Details
| Original language | English |
|---|---|
| Title of host publication | IEEE Conference on Games 2019, CoG 2019 |
| Publisher | IEEE Computer Society |
| ISBN (electronic) | 9781728118840 |
| Publication status | Published - Aug 2019 |
| Externally published | Yes |
| Event | 2019 IEEE Conference on Games, CoG 2019 - London, United Kingdom (UK) Duration: 20 Aug 2019 → 23 Aug 2019 |
Publication series
| Name | IEEE Conference on Computatonal Intelligence and Games, CIG |
|---|---|
| Volume | 2019-August |
| ISSN (Print) | 2325-4270 |
| ISSN (electronic) | 2325-4289 |
Abstract
This paper investigates the effect of learning a forward model on the performance of a statistical forward planning agent. We transform Conway's Game of Life simulation into a single-player game where the objective can be either to preserve as much life as possible or to extinguish all life as quickly as possible.In order to learn the forward model of the game, we formulate the problem in a novel way that learns the local cell transition function by creating a set of supervised training data and predicting the next state of each cell in the grid based on its current state and immediate neighbours. Using this method we are able to harvest sufficient data to learn perfect forward models by observing only a few complete state transitions, using either a look-up table, a decision tree, or a neural network.In contrast, learning the complete state transition function is a much harder task and our initial efforts to do this using deep convolutional auto-encoders were less successful.We also investigate the effects of imperfect learned models on prediction errors and game-playing performance, and show that even models with significant errors can provide good performance.
Keywords
- Decision Tree, Forward Model Learning, General Game Playing/Learning, Neural Networks, Rolling Horizon Evolutionary Algorithm
ASJC Scopus subject areas
- Computer Science(all)
- Artificial Intelligence
- Computer Science(all)
- Computer Graphics and Computer-Aided Design
- Computer Science(all)
- Computer Vision and Pattern Recognition
- Computer Science(all)
- Human-Computer Interaction
- Computer Science(all)
- Software
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
IEEE Conference on Games 2019, CoG 2019. IEEE Computer Society, 2019. 8848002 (IEEE Conference on Computatonal Intelligence and Games, CIG; Vol. 2019-August).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - A local approach to forward model learning
T2 - 2019 IEEE Conference on Games, CoG 2019
AU - Lucas, Simon M.
AU - Dockhorn, Alexander
AU - Volz, Vanessa
AU - Bamford, Chris
AU - Gaina, Raluca D.
AU - Bravi, Ivan
AU - Perez-Liebana, Diego
AU - Mostaghim, Sanaz
AU - Kruse, Rudolf
N1 - Funding Information: ACKNOWLEDGMENT This work was partially funded by the EPSRC CDT in Intelligent Games and Game Intelligence (IGGI) EP/L015846/1. Funding Information: This work was partially funded by the EPSRC CDT in Intelligent Games and Game Intelligence (IGGI) EP/L015846/1.
PY - 2019/8
Y1 - 2019/8
N2 - This paper investigates the effect of learning a forward model on the performance of a statistical forward planning agent. We transform Conway's Game of Life simulation into a single-player game where the objective can be either to preserve as much life as possible or to extinguish all life as quickly as possible.In order to learn the forward model of the game, we formulate the problem in a novel way that learns the local cell transition function by creating a set of supervised training data and predicting the next state of each cell in the grid based on its current state and immediate neighbours. Using this method we are able to harvest sufficient data to learn perfect forward models by observing only a few complete state transitions, using either a look-up table, a decision tree, or a neural network.In contrast, learning the complete state transition function is a much harder task and our initial efforts to do this using deep convolutional auto-encoders were less successful.We also investigate the effects of imperfect learned models on prediction errors and game-playing performance, and show that even models with significant errors can provide good performance.
AB - This paper investigates the effect of learning a forward model on the performance of a statistical forward planning agent. We transform Conway's Game of Life simulation into a single-player game where the objective can be either to preserve as much life as possible or to extinguish all life as quickly as possible.In order to learn the forward model of the game, we formulate the problem in a novel way that learns the local cell transition function by creating a set of supervised training data and predicting the next state of each cell in the grid based on its current state and immediate neighbours. Using this method we are able to harvest sufficient data to learn perfect forward models by observing only a few complete state transitions, using either a look-up table, a decision tree, or a neural network.In contrast, learning the complete state transition function is a much harder task and our initial efforts to do this using deep convolutional auto-encoders were less successful.We also investigate the effects of imperfect learned models on prediction errors and game-playing performance, and show that even models with significant errors can provide good performance.
KW - Decision Tree
KW - Forward Model Learning
KW - General Game Playing/Learning
KW - Neural Networks
KW - Rolling Horizon Evolutionary Algorithm
UR - http://www.scopus.com/inward/record.url?scp=85073101101&partnerID=8YFLogxK
U2 - 10.1109/CIG.2019.8848002
DO - 10.1109/CIG.2019.8848002
M3 - Conference contribution
AN - SCOPUS:85073101101
T3 - IEEE Conference on Computatonal Intelligence and Games, CIG
BT - IEEE Conference on Games 2019, CoG 2019
PB - IEEE Computer Society
Y2 - 20 August 2019 through 23 August 2019
ER -