ICML 2021spotlight30 citations

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

Abstract

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.

BibTeX
@InProceedings{pmlr-v139-devlin21a,
  title = 	 {Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation},
  author =       {Devlin, Sam and Georgescu, Raluca and Momennejad, Ida and Rzepecki, Jaroslaw and Zuniga, Evelyn and Costello, Gavin and Leroy, Guy and Shaw, Ali and Hofmann, Katja},
  booktitle = 	 {Proceedings of the 38th International Conference on Machine Learning},
  pages = 	 {2644--2653},
  year = 	 {2021},
  editor = 	 {Meila, Marina and Zhang, Tong},
  volume = 	 {139},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {18--24 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v139/devlin21a/devlin21a.pdf},
  url = 	 {https://proceedings.mlr.press/v139/devlin21a.html},
  abstract = 	 {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.}
}
Navigation Turing Test (NTT): Learning to Evaluate Human-Like Navigation · ICML 2021