Timezone: »

 
Inferring the Goals of Communicating Agents from Actions and Instructions
Lance Ying · Tan Zhi-Xuan · Vikash Mansinghka · Josh Tenenbaum

Fri Jul 28 03:15 PM -- 04:30 PM (PDT) @
in Workshop on Theory of Mind in Communicating Agents »
Event URL: https://openreview.net/forum?id=TBWhdZUOwO »
When humans cooperate, they frequently coordinate their activity through both verbal communication and non-verbal actions, using this information to infer a shared goal and plan. How can we model this inferential ability? In this paper, we introduce a model of a cooperative team where one agent, the principal, may communicate natural language instructions about their shared plan to another agent, the assistant, using GPT-3 as a likelihood function for instruction utterances. We then show how a third person observer can infer the team's goal via multi-modal Bayesian inverse planning from actions and instructions, computing the posterior distribution over goals under the assumption that agents will act and communicate rationally to achieve them. We evaluate this approach by comparing it with human goal inferences in a multi-agent gridworld, finding that our model's inferences closely correlate with human judgments $(R = 0.96)$. When compared to inference from actions alone, we also find that instructions lead to more rapid and less uncertain goal inference, highlighting the importance of verbal communication for cooperative agents.
Keywords: Probabilistic Programming · Language Models · Inverse Planning · Bayesian Theory of Mind · Cooperation · Language Understanding

Author Information

Lance Ying (School of Engineering and Applied Sciences, Harvard University)
Tan Zhi-Xuan (Massachusetts Institute of Technology)
Vikash Mansinghka (Massachusetts Institute of Technology)
Josh Tenenbaum (MIT)

Joshua Brett Tenenbaum is Professor of Cognitive Science and Computation at the Massachusetts Institute of Technology. He is known for contributions to mathematical psychology and Bayesian cognitive science. He previously taught at Stanford University, where he was the Wasow Visiting Fellow from October 2010 to January 2011. Tenenbaum received his undergraduate degree in physics from Yale University in 1993, and his Ph.D. from MIT in 1999. His work primarily focuses on analyzing probabilistic inference as the engine of human cognition and as a means to develop machine learning.

More from the Same Authors