“…Embodied AI. The development of learning-based embodied AI agents has made significant progress across a wide variety of tasks, including: scene rearrangement [3,17,38], object-goal navigation [1,6,8,19,41,43], point-goal navigation [1,19,30,31,40], scene exploration [7,10], embodied question answering [12,18], instructional navigation [2,35], object manipulation [14,44], home task completion with explicit instructions [27,35,36], active visual learning [9,15,20,39], and collaborative task completion with agent-human conversations [29]. While these works have driven much progress in embodied AI, ours is the first agent to tackle the task of tidying up rooms, which requires commonsense reasoning about whether or not an object is out of place, and inferring where it belongs in the context of the room.…”