This Python agent placed 1st out of 646 teams in Lux AI Season 2.
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.
You can read my post-competition writeup here.
- Clone this repo and the v2.2.0 runner
- Follow setup instructions described here
- From the Lux-S2-public directory, run a test match
luxai-s2 ./main.py ./main.py -v 1 -o replay.html -s 0 -l 1000
- This may take up to an hour to run. For a quicker runtime, reduce FUTURE_LEN to 5.
- To view a replay of the match, open replay.html e.g.
file:///path/to/Lux-S2-public/replay.html
in a browser (you will have to modify the path in the URL).