English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Multiple Artificial Intelligence (AI) methods have been proposed over recentyears to create controllers to play multiple video games of different natureand complexity without revealing the specific mechanics of each of these gamesto the AI methods. In recent years, Evolutionary Algorithms (EAs) employingrolling horizon mechanisms have achieved extraordinary results in these type ofproblems. However, some limitations are present in Rolling Horizon EAs makingit a grand challenge of AI. These limitations include the wasteful mechanism ofcreating a population and evolving it over a fraction of a second to propose anaction to be executed by the game agent. Another limitation is to use a scalarvalue (fitness value) to direct evolutionary search instead of accounting for amechanism that informs us how a particular agent behaves during the rollinghorizon simulation. In this work, we address both of these issues. We introducethe use of a statistical tree that tackles the latter limitation. Furthermore,we tackle the former limitation by employing a mechanism that allows us to seedpart of the population using Monte Carlo Tree Search, a method that hasdominated multiple General Video Game AI competitions. We show how the proposednovel mechanism, called Statistical Tree-based Population Seeding, achievesbetter results compared to vanilla Rolling Horizon EAs in a set of 20 games,including 10 stochastic and 10 deterministic games.

Statistical Tree-based Population Seeding for Rolling Horizon EAs in General Video Game Playing