Details
| Original language | English |
|---|---|
| Title of host publication | 2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 2085-2092 |
| Number of pages | 8 |
| ISBN (electronic) | 9781728183923 |
| Publication status | Published - 2021 |
| Externally published | Yes |
| Event | 2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Virtual, Krakow, Poland Duration: 28 Jun 2021 → 1 Jul 2021 |
Publication series
| Name | 2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings |
|---|
Abstract
Portfolio methods represent a simple but efficient type of action abstraction which has shown to improve the performance of search-based agents in a range of strategy games. We first review existing portfolio techniques and propose a new algorithm for optimization and action-selection based on the Rolling Horizon Evolutionary Algorithm. Moreover, a series of variants are developed to solve problems in different aspects. We further analyze the performance of discussed agents in a general strategy game-playing task. For this purpose, we run experiments on three different game-modes of the STRATEGA framework. For the optimization of the agents' parameters and portfolio sets we study the use of the N-tuple Bandit Evolutionary Algorithm. The resulting portfolio sets suggest a high diversity in play-styles while being able to consistently beat the sample agents. An analysis of the agents' performance shows that the proposed algorithm generalizes well to all game-modes and is able to outperform other portfolio methods.
Keywords
- General strategy game-playing, N-tuple bandit evolutionary algorithm, Portfolio methods, Stratega
ASJC Scopus subject areas
- Mathematics(all)
- Modelling and Simulation
- Mathematics(all)
- Computational Mathematics
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2021. p. 2085-2092 (2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Portfolio Search and Optimization 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: ACKNOWLEDGEMENTS This work is supported by UK EPSRC research grant EP/T008962/1 (https://gaigresearch.github.io/afm/).
PY - 2021
Y1 - 2021
N2 - Portfolio methods represent a simple but efficient type of action abstraction which has shown to improve the performance of search-based agents in a range of strategy games. We first review existing portfolio techniques and propose a new algorithm for optimization and action-selection based on the Rolling Horizon Evolutionary Algorithm. Moreover, a series of variants are developed to solve problems in different aspects. We further analyze the performance of discussed agents in a general strategy game-playing task. For this purpose, we run experiments on three different game-modes of the STRATEGA framework. For the optimization of the agents' parameters and portfolio sets we study the use of the N-tuple Bandit Evolutionary Algorithm. The resulting portfolio sets suggest a high diversity in play-styles while being able to consistently beat the sample agents. An analysis of the agents' performance shows that the proposed algorithm generalizes well to all game-modes and is able to outperform other portfolio methods.
AB - Portfolio methods represent a simple but efficient type of action abstraction which has shown to improve the performance of search-based agents in a range of strategy games. We first review existing portfolio techniques and propose a new algorithm for optimization and action-selection based on the Rolling Horizon Evolutionary Algorithm. Moreover, a series of variants are developed to solve problems in different aspects. We further analyze the performance of discussed agents in a general strategy game-playing task. For this purpose, we run experiments on three different game-modes of the STRATEGA framework. For the optimization of the agents' parameters and portfolio sets we study the use of the N-tuple Bandit Evolutionary Algorithm. The resulting portfolio sets suggest a high diversity in play-styles while being able to consistently beat the sample agents. An analysis of the agents' performance shows that the proposed algorithm generalizes well to all game-modes and is able to outperform other portfolio methods.
KW - General strategy game-playing
KW - N-tuple bandit evolutionary algorithm
KW - Portfolio methods
KW - Stratega
UR - http://www.scopus.com/inward/record.url?scp=85110943253&partnerID=8YFLogxK
U2 - 10.1109/CEC45853.2021.9504824
DO - 10.1109/CEC45853.2021.9504824
M3 - Conference contribution
AN - SCOPUS:85110943253
T3 - 2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings
SP - 2085
EP - 2092
BT - 2021 IEEE Congress on Evolutionary Computation, CEC 2021 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE Congress on Evolutionary Computation, CEC 2021
Y2 - 28 June 2021 through 1 July 2021
ER -