Ask4Help: Learning to Leverage an Expert for Embodied Tasks

TL;DR

Ask4Help enables embodied AI agents to request expert assistance, significantly improving task success rates with minimal help, by training policies that balance performance and help cost without altering the original agent.

Contribution

The paper introduces Ask4Help, a novel approach allowing agents to learn when and how to request expert help, improving performance efficiently without modifying existing models.

Findings

Object navigation success increases from 52% to 86% with 13% help.

Room rearrangement success rises from 7% to 90.4% with 39% help.

Human trials confirm practical effectiveness of Ask4Help.

Abstract

Embodied AI agents continue to become more capable every year with the advent of new models, environments, and benchmarks, but are still far away from being performant and reliable enough to be deployed in real, user-facing, applications. In this paper, we ask: can we bridge this gap by enabling agents to ask for assistance from an expert such as a human being? To this end, we propose the Ask4Help policy that augments agents with the ability to request, and then use expert assistance. Ask4Help policies can be efficiently trained without modifying the original agent's parameters and learn a desirable trade-off between task performance and the amount of requested help, thereby reducing the cost of querying the expert. We evaluate Ask4Help on two different tasks -- object goal navigation and room rearrangement and see substantial improvements in performance using minimal help. On object navigation, an agent that achieves a $52\%$ success rate is raised to $86\%$ with $13\%$ help and for rearrangement, the state-of-the-art model with a $7\%$ success rate is dramatically improved to $90.4\%$ using $39\%$ help. Human trials with Ask4Help demonstrate the efficacy of our approach in practical scenarios. We release the code for Ask4Help here: https://github.com/allenai/ask4help.