The Lux AI Challenge is a competition where competitors design agents to tackle a multi-variable optimization, resource gathering, and allocation problem in a 1v1 scenario against other competitors. In addition to optimization, successful agents must be capable of analyzing their opponents and developing appropriate policies to get the upper hand.
Each day your team is able to submit up to 5 agents (bots) to the competition. Each submission will play Episodes (games) against other bots on the ladder that have a similar skill rating. Over time skill ratings will go up with wins or down with losses and evened out with ties.
At the conclusion of 360 turns the winner is whichever team has the most CityTiles on the map. If that is a tie, then whichever team has the most units owned on the board wins. If still a tie, the game is marked as a tie.
I will be going two weeks on holidays from 25 September and around 10 days from 26 November. So instead of having 3 months for the challenge I will be having slightly more than 2 months.
Moreover I will be missing on the last days of the challenge. Thus I need to have in mind that I need to end the challenge before the other participants.
I don't currently have other project competing for resources.
I need to deeply understand the game previously to deciding the approach. To do so I will start by designing an agent by hand. This will help to find where machine learning could be applied.