Learning a Hierarchical Planner from Humans in Multiple Generations

TL;DR

This paper introduces a natural programming system that combines hierarchical planning with a library of decompositions, enabling machines to learn from human interactions and adapt to new contexts more efficiently.

Contribution

It presents a novel library learning system that integrates programmatic learning with hierarchical planning and linguistic hints for improved adaptability.

Findings

Robustly composes programs from multiple users and contexts.

Adapts faster and solves more complex tasks than baseline methods.

Demonstrated effectiveness through simulated studies and a human experiment with 360 participants.

Abstract

A typical way in which a machine acquires knowledge from humans is by programming. Compared to learning from demonstrations or experiences, programmatic learning allows the machine to acquire a novel skill as soon as the program is written, and, by building a library of programs, a machine can quickly learn how to perform complex tasks. However, as programs often take their execution contexts for granted, they are brittle when the contexts change, making it difficult to adapt complex programs to new contexts. We present natural programming, a library learning system that combines programmatic learning with a hierarchical planner. Natural programming maintains a library of decompositions, consisting of a goal, a linguistic description of how this goal decompose into sub-goals, and a concrete instance of its decomposition into sub-goals. A user teaches the system via curriculum building, by identifying a challenging yet not impossible goal along with linguistic hints on how this goal may be decomposed into sub-goals. The system solves for the goal via hierarchical planning, using the linguistic hints to guide its probability distribution in proposing the right plans. The system learns from this interaction by adding newly found decompositions in the successful search into its library. Simulated studies and a human experiment (n=360) on a controlled environment demonstrate that natural programming can robustly compose programs learned from different users and contexts, adapting faster and solving more complex tasks when compared to programmatic baselines.