I am currently doing research under Risto Miikkulainen of the
Neural Networks Research Group.
I'm interested in automatic discovery of complex multi-modal behavior, particularly in the domain of real-time games.
Agents that can behave in different manners in response to different situations are crucial for games because
human players adapt so quickly. If a game's NPCs can learn multiple different behaviors to respond to
humans' adaptive behaviors, then the game is more challenging and more fun.
This work makes use of the simulation environment BREVE.
Animations of evolved behavior learned in a battle domain can be seen here.
