Navigates Like Me: Understanding How People Evaluate Human-Like AI in Video Games Article Swipe
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.1145/3544548.3581348
· OA: W4323547460
We aim to understand how people assess human likeness in navigation produced\nby people and artificially intelligent (AI) agents in a video game. To this\nend, we propose a novel AI agent with the goal of generating more human-like\nbehavior. We collect hundreds of crowd-sourced assessments comparing the\nhuman-likeness of navigation behavior generated by our agent and baseline AI\nagents with human-generated behavior. Our proposed agent passes a Turing Test,\nwhile the baseline agents do not. By passing a Turing Test, we mean that human\njudges could not quantitatively distinguish between videos of a person and an\nAI agent navigating. To understand what people believe constitutes human-like\nnavigation, we extensively analyze the justifications of these assessments.\nThis work provides insights into the characteristics that people consider\nhuman-like in the context of goal-directed video game navigation, which is a\nkey step for further improving human interactions with AI agents.\n
