A Local Approach to Forward Model Learning: Results on the Game of Life Game
2019
Simon M Lucas and Alexander Dockhorn and Vanessa Volz and Chris Bamford and Raluca D. Gaina and Ivan Bravi and Diego Perez-Liebana and Sanaz Mostaghim and Rudolf Kruse
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.
Arxiv: https://arxiv.org/abs/1903.12508
URL: https://ieeexplore.ieee.org/document/8848002
DOI:10.1109/CIG.2019.8848002
Cite this work
@inproceedings{lucas2019gog, author= {Simon M Lucas and Alexander Dockhorn and Vanessa Volz and Chris Bamford and Raluca D. Gaina and Ivan Bravi and Diego Perez-Liebana and Sanaz Mostaghim and Rudolf Kruse}, title= {{A Local Approach to Forward Model Learning: Results on the Game of Life Game}}, year= {2019}, booktitle= {{IEEE Conference on Games (COG)}}, pages= {1--8}, url= {https://ieeexplore.ieee.org/document/8848002}, doi= {10.1109/CIG.2019.8848002}, 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.},
}