Timezone: »

 
Spotlight
Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation
Sam Devlin · Raluca Georgescu · Ida Momennejad · Jaroslaw Rzepecki · Evelyn Zuniga · Gavin Costello · Guy Leroy · Ali Shaw · Katja Hofmann

Tue Jul 20 05:20 AM -- 05:25 AM (PDT) @
in Deep Learning Applications »

A key challenge on the path to developing agents that learn complex human-like behavior is the need to quickly and accurately quantify human-likeness. While human assessments of such behavior can be highly accurate, speed and scalability are limited. We address these limitations through a novel automated Navigation Turing Test (ANTT) that learns to predict human judgments of human-likeness. We demonstrate the effectiveness of our automated NTT on a navigation task in a complex 3D environment. We investigate six classification models to shed light on the types of architectures best suited to this task, and validate them against data collected through a human NTT. Our best models achieve high accuracy when distinguishing true human and agent behavior. At the same time, we show that predicting finer-grained human assessment of agents’ progress towards human-like behavior remains unsolved. Our work takes an important step towards agents that more effectively learn complex human-like behavior.

Keywords: Algorithms · Algorithms Evaluation

Author Information

Sam Devlin (Microsoft Research)
Raluca Georgescu (Microsoft Research)
Ida Momennejad (Microsoft Research)
Jaroslaw Rzepecki (Microsoft Research)
Evelyn Zuniga (Microsoft Research)
Gavin Costello (Ninja Theory)
Guy Leroy (Microsoft Research)
Ali Shaw (Ninja Theory)
Katja Hofmann (Microsoft)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors