{"id":19,"date":"2019-09-05T23:13:00","date_gmt":"2019-09-05T23:13:00","guid":{"rendered":"https:\/\/projects-old.etc.cmu.edu\/shadow-agent\/index.php\/mesmerize\/"},"modified":"2019-12-11T19:29:31","modified_gmt":"2019-12-11T19:29:31","slug":"mesmerize","status":"publish","type":"page","link":"https:\/\/projects-old.etc.cmu.edu\/shadow-agent\/","title":{"rendered":"About"},"content":{"rendered":"

Project Shadow Agent is an experimental project exploring new gameplay interactions using reinforcement learning. By working with Google Stadia, the team seeks new game genres and different potential applications.
\n
Reinforcement learning (RL) is a relatively new machine learning method which learns the best actions based on reward or punishment in an environment. The goal of the project is to present a delightful user experience by creating believable characters in a game using existing machine learning tools to train different behaviors of Non-Player Characters (NPCs).<\/p><\/div> <\/div>

<\/div> <\/div><\/div> <\/div>

\u2013\u2013<\/span>
Our Approach<\/span><\/span><\/h2> <\/div> <\/div>
<\/i>

Focus on Interaction<\/h4>

between RL agent and human players in co-op gameplay scenarios<\/p> LEARN MORE<\/a><\/div> <\/div>

<\/i>

Build with ML-Agent plugin<\/span><\/h4>

to set up the pipline on Unity platform to understand the workflow of RL<\/p> LEARN MORE<\/a><\/div> <\/div>

<\/i>

Design a delightful experience<\/span><\/h4>

by utilizing storytelling arc and interest curve that drives fun moments<\/p> LEARN MORE<\/a><\/div> <\/div> <\/div> <\/div><\/div>

\u2013\u2013
Development Blog<\/span><\/h2> <\/div> <\/div>
\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t
\n \n \"\"