Details
| Original language | English |
|---|---|
| Title of host publication | 2021 IEEE Conference on Games, CoG 2021 |
| Publisher | IEEE Computer Society |
| ISBN (electronic) | 9781665438865 |
| Publication status | Published - 2021 |
| Externally published | Yes |
| Event | 2021 IEEE Conference on Games, CoG 2021 - Copenhagen, Denmark Duration: 17 Aug 2021 → 20 Aug 2021 |
Publication series
| Name | IEEE Conference on Computatonal Intelligence and Games, CIG |
|---|---|
| Volume | 2021-August |
| ISSN (Print) | 2325-4270 |
| ISSN (electronic) | 2325-4289 |
Abstract
When implementing intelligent agents for strategy games, we observe that search-based methods struggle with the complexity of such games. To tackle this problem, we propose a new variant of Monte Carlo Tree Search which can incorporate action and game state abstractions. Focusing on the latter, we developed a game state encoding for turn-based strategy games that allows for a flexible abstraction. Using an optimization procedure, we optimize the agent's action and game state abstraction to maximize its performance against a rule-based agent. Furthermore, we compare different combinations of abstractions and their impact on the agent's performance based on the Kill the King game of the Stratega framework. Our results show that action abstractions have improved the performance of our agent considerably. Contrary, game state abstractions have not shown much impact. While these results may be limited to the tested game, they are in line with previous research on abstractions of simple Markov Decision Processes. The higher complexity of strategy games may require more intricate methods, such as hierarchical or time-based abstractions, to further improve the agent's performance.
Keywords
- Action Abstraction, Game State Abstraction, General Strategy Game-playing, Monte Carlo Tree Search, N-Tuple Bandit Evolutionary Algorithm, Stratega
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
2021 IEEE Conference on Games, CoG 2021. IEEE Computer Society, 2021. (IEEE Conference on Computatonal Intelligence and Games, CIG; Vol. 2021-August).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Game State and Action Abstracting Monte Carlo Tree Search for General Strategy Game-Playing
AU - Dockhorn, Alexander
AU - Hurtado-Grueso, Jorge
AU - Jeurissen, Dominik
AU - Xu, Linjie
AU - Perez-Liebana, Diego
N1 - Funding Information: was supported by
PY - 2021
Y1 - 2021
N2 - When implementing intelligent agents for strategy games, we observe that search-based methods struggle with the complexity of such games. To tackle this problem, we propose a new variant of Monte Carlo Tree Search which can incorporate action and game state abstractions. Focusing on the latter, we developed a game state encoding for turn-based strategy games that allows for a flexible abstraction. Using an optimization procedure, we optimize the agent's action and game state abstraction to maximize its performance against a rule-based agent. Furthermore, we compare different combinations of abstractions and their impact on the agent's performance based on the Kill the King game of the Stratega framework. Our results show that action abstractions have improved the performance of our agent considerably. Contrary, game state abstractions have not shown much impact. While these results may be limited to the tested game, they are in line with previous research on abstractions of simple Markov Decision Processes. The higher complexity of strategy games may require more intricate methods, such as hierarchical or time-based abstractions, to further improve the agent's performance.
AB - When implementing intelligent agents for strategy games, we observe that search-based methods struggle with the complexity of such games. To tackle this problem, we propose a new variant of Monte Carlo Tree Search which can incorporate action and game state abstractions. Focusing on the latter, we developed a game state encoding for turn-based strategy games that allows for a flexible abstraction. Using an optimization procedure, we optimize the agent's action and game state abstraction to maximize its performance against a rule-based agent. Furthermore, we compare different combinations of abstractions and their impact on the agent's performance based on the Kill the King game of the Stratega framework. Our results show that action abstractions have improved the performance of our agent considerably. Contrary, game state abstractions have not shown much impact. While these results may be limited to the tested game, they are in line with previous research on abstractions of simple Markov Decision Processes. The higher complexity of strategy games may require more intricate methods, such as hierarchical or time-based abstractions, to further improve the agent's performance.
KW - Action Abstraction
KW - Game State Abstraction
KW - General Strategy Game-playing
KW - Monte Carlo Tree Search
KW - N-Tuple Bandit Evolutionary Algorithm
KW - Stratega
UR - http://www.scopus.com/inward/record.url?scp=85122924332&partnerID=8YFLogxK
U2 - 10.1109/CoG52621.2021.9619029
DO - 10.1109/CoG52621.2021.9619029
M3 - Conference contribution
AN - SCOPUS:85122924332
T3 - IEEE Conference on Computatonal Intelligence and Games, CIG
BT - 2021 IEEE Conference on Games, CoG 2021
PB - IEEE Computer Society
T2 - 2021 IEEE Conference on Games, CoG 2021
Y2 - 17 August 2021 through 20 August 2021
ER -