To build a better AI helper, start by modeling the irrationa

MIT and other researchers developed a framework that models irrational or suboptimal behavior of a human or AI agent, based on their computational constraints. Their technique can help predict an agent’s future actions.

Related Keywords

Jacob Andreas , Athul Paul Jacob , Abhishek Gupta , National Science Foundation , University Of Washington , International Conference On Learning Representations , Artificial Intelligence Laboratory , Computer Science , International Conference , Computing Artificial Intelligence , National Science , Artificial Intelligence , Collaborative Intelligence , Odeling Human Behavior ,