Knegt, S.J.L. (2017) Reinforcement Learning in the Game of Tron using Vision Grids and Opponent Modelling. Bachelor's Thesis, Artificial Intelligence.
|
Text
RLTRON_Final.pdf - Published Version Download (571kB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
Toestemming.pdf - Other Restricted to Backend only Download (78kB) |
Abstract
In this thesis we propose the use of vision grids as state representation to learn the game Tron. This approach speeds up learning by significantly reducing the number of unique states. Secondly, we introduce a novel opponent modelling technique, which is used to predict the opponent's next move. The learned model of the opponent is subsequently used in Monte-Carlo rollouts, in which the game is simulated n-steps ahead in order to determine the expected value of conducting a certain action. Finally, we compare the performance of the agent with two activation functions, namely the sigmoid and exponential linear unit (Elu). The results show that the Elu activation function outperforms the sigmoid activation function in most cases. Secondly, vision grids significantly increase learning speed and in most cases it also increases the agent's performance compared to when the full grid is used as state representation. Finally, the opponent modelling technique allows the agent to learn a model of the opponent, which in combination with Monte-Carlo rollouts significantly increases the agent's performance.
| Item Type: | Thesis (Bachelor's Thesis) |
|---|---|
| Degree programme: | Artificial Intelligence |
| Thesis type: | Bachelor's Thesis |
| Language: | English |
| Date Deposited: | 15 Feb 2018 08:26 |
| Last Modified: | 15 Feb 2018 08:26 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/14911 |
Actions (login required)
 |
View Item |