Timezone: »

 
Building Community Driven Libraries of Natural Programs
Leonardo Hernandez Cano · Yewen Pu · Robert Hawkins · Josh Tenenbaum · Armando Solar-Lezama

@
in Interactive Learning with Implicit Human Feedback »
Event URL: https://openreview.net/forum?id=iRea6QCxi1 »

A typical way in which a machine acquires knowledge from humans is through programs -- sequences of executable commands that can be composed hierarchically. By building a library of programs, a machine can quickly learn how to perform complex tasks. However, as programs are typically created for specific situations, they become brittle when the contexts change, making it difficult compound knowledge learned from different teachers and contexts. We present natural programming, a library building procedure where each program is represented as a \emph{search problem} containing both a goal and linguistic hints on how to decompose it into sub-goals. A natural program is executed via search in a manner of hierarchical planning and guided by a large language model, effectively adapting learned programs to new contexts. After each successful execution, natural programming learns by improving search, rather than memorizing the solution sequence of commands. Simulated studies and a human experiment (n=360) on a simple crafting environment demonstrate that natural programming can robustly compose programs learned from different users and contexts, solving more complex tasks when compared to baselines that maintain libraries of command sequences.

Author Information

Leonardo Hernandez Cano (Massachusetts Institute of Technology)
Yewen Pu (Autodesk)
Robert Hawkins (Princeton University)
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.

Armando Solar-Lezama (MIT)

More from the Same Authors