Integrating Diverse Knowledge Sources for Online One-shot Learning of Novel Tasks
This work addresses the challenge of rapid and reliable task learning for simulated office mobile robots, though it appears incremental as it builds on existing cognitive architectures and knowledge sources.
The paper tackled the problem of enabling autonomous agents to learn new tasks online with minimal human input by integrating diverse knowledge sources, and the result was an improvement in one-shot task learning that reduced the need for human feedback.
Autonomous agents are able to draw on a wide variety of potential sources of task knowledge; however current approaches invariably focus on only one or two. Here we investigate the challenges and impact of exploiting diverse knowledge sources to learn online, in one-shot, new tasks for a simulated office mobile robot. The resulting agent, developed in the Soar cognitive architecture, uses the following sources of domain and task knowledge: interaction with the environment, task execution and search knowledge, human natural language instruction, and responses retrieved from a large language model (GPT-3). We explore the distinct contributions of these knowledge sources and evaluate the performance of different combinations in terms of learning correct task knowledge and human workload. Results show that an agent's online integration of diverse knowledge sources improves one-shot task learning overall, reducing human feedback needed for rapid and reliable task learning.