Timezone: »
When deployed, AI agents will encounter problems that are beyond their autonomous problem-solving capabilities. Leveraging human assistance can help agents overcome their inherent limitations and robustly cope with unfamiliar situations. We present a general interactive framework that enables an agent to request and interpret rich, contextually useful information from an assistant that has knowledge about the task and the environment. We demonstrate the practicality of our framework on a simulated human-assisted navigation problem. Aided with an assistance-requesting policy learned by our method, a navigation agent achieves up to a 7× improvement in success rate on tasks that take place in previously unseen environments, compared to fully autonomous behavior. We show that the agent can take advantage of different types of information depending on the context, and analyze the benefits and challenges of learning the assistance-requesting policy when the assistant can recursively decompose tasks into subtasks.
Author Information
Khanh Nguyen (University of Maryland)
Yonatan Bisk (Carnegie Mellon University)
Hal Daumé III (Microsoft Research / University of Maryland)
Related Events (a corresponding poster, oral, or spotlight)
-
2022 Spotlight: A Framework for Learning to Request Rich and Contextually Useful Information from Humans »
Thu. Jul 21st 03:35 -- 03:40 PM Room Room 310
More from the Same Authors
-
2023 : Adapting to Gradual Distribution Shifts with Continual Weight Averaging »
Jared Fernandez · Saujas Vaduguru · Sanket Vaibhav Mehta · Yonatan Bisk · Emma Strubell -
2022 Poster: Symmetric Machine Theory of Mind »
Melanie Sclar · Graham Neubig · Yonatan Bisk -
2022 Spotlight: Symmetric Machine Theory of Mind »
Melanie Sclar · Graham Neubig · Yonatan Bisk -
2021 Poster: Few-shot Language Coordination by Modeling Theory of Mind »
Hao Zhu · Graham Neubig · Yonatan Bisk -
2021 Spotlight: Few-shot Language Coordination by Modeling Theory of Mind »
Hao Zhu · Graham Neubig · Yonatan Bisk -
2021 Poster: Interactive Learning from Activity Description »
Khanh Nguyen · Dipendra Misra · Robert Schapire · Miroslav Dudik · Patrick Shafto -
2021 Spotlight: Interactive Learning from Activity Description »
Khanh Nguyen · Dipendra Misra · Robert Schapire · Miroslav Dudik · Patrick Shafto -
2017 Poster: Active Learning for Cost-Sensitive Classification »
Akshay Krishnamurthy · Alekh Agarwal · Tzu-Kuo Huang · Hal Daumé III · John Langford -
2017 Talk: Active Learning for Cost-Sensitive Classification »
Akshay Krishnamurthy · Alekh Agarwal · Tzu-Kuo Huang · Hal Daumé III · John Langford