Читать книгу Cyberphysical Smart Cities Infrastructures - Группа авторов - Страница 41

Embodied Question Answering brings QA into the embodied world. The task starts by an agent being spawned at a random location in a 3D environment and asked a question in which its answer can be found somewhere in the environment. For the agent to answer it, it must first strategically navigate to explore the environment, gather necessary data via its vision, and then answer the question when the agent finds it [52, 53].

Following this, Das et al. [54] also presented a modular approach to further enhance this process by teaching the agent to break the master policy into subgoals that are also interpretable by humans and execute them to answer the question. This proved to increase the success rate.