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
Many potential applications of artificial intelligence involve making real-time decisions in physical systems while interacting with humans. Automobile racing represents an extreme example of these conditions; drivers must execute complex tactical manoeuvres to pass or block…
Planetary rovers have a limited sensory horizon and operate in environments where limited information about the surrounding terrain is available. The rough and unknown nature of the terrain in planetary environments potentially leads to scenarios where the rover gets stuckan…
Sparse-reward environments are famously challenging for deep reinforcement learning (DRL) algorithms. Yet, the prospect of solving intrinsically sparse tasks in an end-to-end fashion without any extra reward engineering is highly appealing. Such aspiration has recently led t…
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.
