Fight to the death with AI robots

NERO_screenshot2_small.jpgNERO is an award-winning futuristic computer game where the player trains squadrons of android soldiers, to be released and pitted against soldiers trained by another player.

Crucially, the android soliders learn using a neural network that adapts via a genetic algorithm.

For the NERO project we are using a specific neuroevolutionary algorithm called NEAT, Neuro-Evolution of Augmenting Topologies. Unlike most neuroevolutionary algorithms, NEAT starts with an artificial neural network of minimal connectivity and adds complexity only when it helps solve a problem. This helps ensure that the algorithm does not produce unnecessarily complex solutions.

In NERO we are introducing a new real-time variant of NEAT, called rtNEAT, in which a small population evolves while you watch. (Most genetic algorithms use generation-based off-line processing, and only provide a result at the end of some pre-specified amount of training.)

The neural network is based on published research and the documentation page contains a raft of information on game play and the science behind the software.

There’s screenshots and video of the game in action, and it’s free to download.

Link to website for NERO.

Post a Comment

Required fields are marked *
*
*

Follow

Get every new post delivered to your Inbox.

Join 23,533 other followers