Abstract
Applying LCS/XCS to the RTS Games Domain
Highlights
Real-Time Strategy (RTS) games are a sub-genre of strategy computer games based on classical board games like chess or tic-tac-toe
Battles constitute a significant part of the Real-Time Strategy games (RTS) games, and a good performance is desired in such localised matches
This paper has presented a game agent which uses a group of XCS algorithms that form a single player-actionsset as an output result and applied it to the RTS games domain
Summary
Real-Time Strategy (RTS) games are a sub-genre of strategy computer games based on classical board games like chess or tic-tac-toe. RTS games are high complexity games [1] because: the number of involved units is high (at one single time it can surpass several hundred units); information presented to the player can be imperfect (e.g. parts of a map can be hidden) or incomplete (e.g. information, about what kind of units the opponent chose to play with, is unknown to the player); randomness, uncertainty and non-deterministic behaviour can be included in the game engine operation; temporal continuity (the previous action constrains future action(s)); etc. This high computational complexity motivated an article from Buro [2], which was published in 2003, with the idea that RTS games can be used not just for gaming, and as testbeds for Artificial Intelligence (AI) research
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Similar Papers
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.