Abstract
While traditionally a labour intensive task, the testing of game content is progressively becoming more automated.
Among the many directions in which this automation is taking shape, automatic play-testing is one of the most promising thanks also to advancements of many supervised and reinforcement learning (RL) algorithms.
However these type of algorithms, while extremely powerful, often suffer in production environments due to issues with reliability and transparency in their training and usage.
In this research work we are investigating and evaluating strategies to apply the popular RL method Proximal Policy Optimization (PPO) in a casual mobile puzzle game with a specific focus on improving its reliability in training and generalization during game playing.
We have implemented and tested a number of different strategies against a real-world mobile puzzle game (Lily's Garden from Tactile Games).
We isolated the conditions that lead to a failure in either training or generalization during testing and we identified a few strategies to ensure a more stable behaviour of the algorithm in this game genre.
Among the many directions in which this automation is taking shape, automatic play-testing is one of the most promising thanks also to advancements of many supervised and reinforcement learning (RL) algorithms.
However these type of algorithms, while extremely powerful, often suffer in production environments due to issues with reliability and transparency in their training and usage.
In this research work we are investigating and evaluating strategies to apply the popular RL method Proximal Policy Optimization (PPO) in a casual mobile puzzle game with a specific focus on improving its reliability in training and generalization during game playing.
We have implemented and tested a number of different strategies against a real-world mobile puzzle game (Lily's Garden from Tactile Games).
We isolated the conditions that lead to a failure in either training or generalization during testing and we identified a few strategies to ensure a more stable behaviour of the algorithm in this game genre.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the International Conference on the Foundations of Digital Games |
| Publisher | Association for Computing Machinery |
| Publication date | 2020 |
| ISBN (Electronic) | 9781450388078 |
| DOIs | |
| Publication status | Published - 2020 |
| Event | FDG 2020: Foundations of Digitale Games - Malta, Malta Duration: 16 Sept 2020 → 18 Sept 2020 Conference number: 2020 http://fdg2020.org/ http://fdg2020.org |
Conference
| Conference | FDG 2020: Foundations of Digitale Games |
|---|---|
| Number | 2020 |
| Location | Malta |
| Country/Territory | Malta |
| Period | 16/09/2020 → 18/09/2020 |
| Internet address |
Keywords
- Game content testing
- Automatic play-testing
- Supervised learning
- Reinforcement learning
- Proximal Policy Optimization (PPO)
- Mobile puzzle games
- Reliability in training
- Algorithm generalization
- Machine learning algorithms
- Game AI