Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration
arXiv:2010.09890
Abstract
In this paper, we introduce Watch-And-Help (WAH), a challenge for testing social intelligence in agents. In WAH, an AI agent needs to help a human-like agent perform a complex household task efficiently. To succeed, the AI agent needs to i) understand the underlying goal of the task by watching a single demonstration of the human-like agent performing the same task (social perception), and ii) coordinate with the human-like agent to solve the task in an unseen environment as fast as possible (human-AI collaboration). For this challenge, we build VirtualHome-Social, a multi-agent household environment, and provide a benchmark including both planning and learning based baselines. We evaluate the performance of AI agents with the human-like agent as well as with real humans using objective metrics and subjective user ratings. Experimental results demonstrate that the proposed challenge and virtual environment enable a systematic evaluation on the important aspects of machine social intelligence at scale.
ICLR 2021
References in corpus (9)
- Emergent Tool Use From Multi-Agent Autocurricula
- The Hanabi Challenge: A New Frontier for AI Research
- ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation
- Gated-Attention Architectures for Task-Oriented Language Grounding
- On the Utility of Learning about Humans for Human-AI Coordination
- Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning
- Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents
- VRKitchen: an Interactive 3D Virtual Environment for Task-oriented Learning
- Embodied Question Answering in Photorealistic Environments with Point Cloud Perception