Tafl-ES: Exploring Evolution Strategies for Asymmetrical Board Games
Roberto Gallotta*
* External authors
AIxIA 2021
2021
Abstract
NeuroEvolution Strategies (NES) are a subclass of Evolution Strategies (ES). While their application to games and board games have been studied in the past [11], current state of the art in most of the games is still held by classic RL models, such as AlphaGo Zero [16]. This is despite recent work showing their desirable properties [12]. In this paper we use NES applied to the board game Hnefatafl, a known hard environment given its asymmetrical nature. In the experiment we set up we coevolve two populations of intelligent agents. With results collected thus far we show the validity of this approach and useful techniques to overcome its large computation resource and time requirements.
Related Publications
Providing neural networks with the ability to learn new tasks sequentially represents one of the main challenges in artificial intelligence. Unlike humans, neural networks are prone to losing previously acquired knowledge upon learning new information, a phenomenon known as …
Graph Neural Networks (GNNs) have proven their effectiveness in various graph-structured data applications. However, one of the significant challenges in the realm of GNNs is representation learning, a critical concept that bridges graph pooling, aimed at creating compressed…
Contextual integration is fundamental to human language comprehension. Language models are a powerful tool for studying how contextual information influences brain activity. In this work, we analyze the brain alignment of three types of language models, which vary in how the…
JOIN US
Shape the Future of AI with Sony AI
We want to hear from those of you who have a strong desire
to shape the future of AI.
