Evaluating Diverse Knowledge Sources for Online One-shot Learning of Novel Tasks

08/19/2022
by   James R. Kirk, et al.
17

Online autonomous agents are able to draw on a wide variety of potential sources of task knowledge; however current approaches invariably focus on only one or two. Here we investigate the challenges and impact of exploiting diverse knowledge sources to learn, in one-shot, new tasks for a simulated household mobile robot. The resulting agent, developed in the Soar cognitive architecture, uses the following sources of domain and task knowledge: interaction with the environment, task execution and planning knowledge, human natural language instruction, and responses retrieved from a large language model (GPT-3). We explore the distinct contributions of these knowledge sources and evaluate the performance of different combinations in terms of learning correct task knowledge, human workload, and computational costs. The results from combining all sources demonstrate that integration improves one-shot task learning overall in terms of computational costs and human workload.

READ FULL TEXT

page 1

page 5

research
09/13/2022

Improving Language Model Prompting in Support of Semi-autonomous Task Learning

Language models (LLMs) offer potential as a source of knowledge for agen...
research
06/11/2023

Improving Knowledge Extraction from LLMs for Robotic Task Learning through Agent Analysis

Large language models (LLMs) offer significant promise as a knowledge so...
research
02/19/2020

Knowledge Reconciliation of n-ary Relations

In the expanding Semantic Web, an increasing number of sources of data a...
research
10/29/2021

MetaICL: Learning to Learn In Context

We introduce MetaICL (Meta-training for In-Context Learning), a new meta...
research
07/12/2022

Inner Monologue: Embodied Reasoning through Planning with Language Models

Recent works have shown how the reasoning capabilities of Large Language...
research
04/09/2016

Towards an Indexical Model of Situated Language Comprehension for Cognitive Agents in Physical Worlds

We propose a computational model of situated language comprehension base...
research
09/13/2019

Learning Household Task Knowledge from WikiHow Descriptions

Commonsense procedural knowledge is important for AI agents and robots t...

Please sign up or login with your details

Forgot password? Click here to reset