论文标题
Ask4Help：学习利用专家进行具体任务
Ask4Help: Learning to Leverage an Expert for Embodied Tasks
论文作者
论文摘要
随着新模型，环境和基准的出现，体现的AI代理商每年都会变得更加能够变得更加有能力，但仍然远离表现且可靠的能力足以将其部署在实际，面向用户的应用程序中。在本文中，我们要求：我们可以通过使代理商能够向像人类这样的专家寻求帮助来弥合这一差距吗？为此，我们提出了Ask4HELP政策，该政策增强了代理商的要求，然后使用专家协助。 ASK4HELP策略可以进行有效培训，而无需修改原始代理的参数，并在任务绩效和请求的帮助数量之间学习理想的权衡，从而降低了查询专家的成本。我们在两个不同的任务上评估Ask4Help - 对象目标导航和房间重排，并使用最小的帮助看到了性能的实质性改善。在对象导航上，实现$ 52 \％$成功率的代理商将提高到$ 86 \％$ $，$ 13 \％$ $ helps，对于重新安排，使用$ 39 \％$ 39 \％$ $ $ $ $ $ $ $ $ 90.4 \％$ $ 90.4 \％\％\％\％\％\％。用Ask4Help进行的人体试验证明了我们在实际情况下方法的功效。我们在此处发布Ask4Help的代码：https：//github.com/allenai/ask4help。
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.
