Xpilot

Give me back that beautiful background!

X-pilot is a client-server, multiuser, dynamic game.

In this precise moment a bunch of humans are wasting their lives chasing each other, playing xpilot.

Here's a plan for AI-attacking them:

• 1. Put up a million stupid programs playing against each other to evolve a better one.

• 2. Launch the bastard into the internet and:

• (a) Pass the x-pilot Turing test (fool other players by behaving humanly)

• (b) Kill them all!

So, this is too difficult. The game is far too complicated for this kind of approach, there are too many rules and variations and weapons, etc. etc.

Tractable subproblems:

• Simplified, no maze, no gravity, no shields, empty-space plain xpilot.

• "Second degree" pursuer-evader game (control acceleration instead of direction). This could be sold to the NASA

• In Koza (Pacman) style, hack high level behaviors ("attack", "explore", "run", etc) and inputs ("distance to closest enemy/wall", "being fired upon", etc.) and adapt a learning algorithm to work on these: Pablo's memorybase!

Results:

• The differential game was solved
• The solution was a little puzzling
• Inputs were hacked to be used by the bot:
• (x,y) coordinates
• Aiming angle
• Angle to nearest enemy
• Distance to nearest enemy
• Density of enemies in neighborhood
• Coordinates of nearest enemy
• Density of bullets in neighborhood
• Behaviors were hacked as well:
• Nil
• Shoot at nearest enemy
• Wander
• Stop
• Approach nearest enemy
• Approach & Shoot
• The differential game studied was of little use when it came to program these behaviors
• Memorybase learning got one conclusion: SHOOT ALL THE TIME!!
• Future research?
• Find a heuristic mathematical strategy useful in the real world.
• Is memorybase a valid learning model?
• Improve inputs & behaviors

Comments? Want to play? Send feedback!