Multi-agent Adaptive AI

I am experimenting on a system with 2 agent with centralize control  and will move together with the player to corner evadors.

The planning model combines path-finding and graph plan when get close to target. A learning model is used to learn the best order of finishing sub-task. Also, it takes data from real player from which I am try to extract the transition model for robots to whether “Cooperate” or “defect” with player.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s