Language models (LLMs) offer potential as a source of knowledge for agents that need to acquire new task competencies within a performance environment. We describe efforts toward a novel agent capability that can construct cues (or "prompts") that result in useful LLM responses for an agent learning a new task. Importantly, responses must not only be "reasonable" (a measure used commonly in research on knowledge extraction from LLMs) but also specific to the agent's task context and in a form that the agent can interpret given its native language capacities. We summarize a series of empirical investigations of prompting strategies and evaluate responses against the goals of targeted and actionable responses for task learning. Our results demonstrate that actionable task knowledge can be obtained from LLMs in support of online agent task learning.
Online 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, in one-shot, new tasks for a simulated household 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 planning 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, human workload, and computational costs. The results from combining all sources demonstrate that integration improves one-shot task learning overall in terms of computational costs and human workload.
This paper is the recommended initial reading for a functional overview of Soar, version 9.6. It includes an abstract overview of the architectural structure of Soar including its processing, memories, learning modules, their interfaces, and the representations of knowledge used by those modules. From there it describes the processing supported by those modules, including decision making, impasses and substates, procedure learning via chunking, reinforcement learning, semantic memory, episodic memory, and spatial-visual reasoning. It then reviews the levels of decision making and variety of learning in Soar, and analysis of Soar as an architecture supporting general human-level AI. Following the references is an appendix that contains short descriptions of recent Soar agents and a glossary of the terminology we use in describing Soar.
This is a detailed analysis and comparison of the ACT-R and Soar cognitive architectures, including their overall structure, their representations of agent data and metadata, and their associated processing. It focuses on working memory, procedural memory, and long-term declarative memory. I emphasize the commonalities, which are many, but also highlight the differences. I identify the processes and distinct classes of information used by these architectures, including agent data, metadata, and meta-process data, and explore the roles that metadata play in decision making, memory retrievals, and learning.
Language models (LMs) are sentence-completion engines trained on massive corpora. LMs have emerged as a significant breakthrough in natural-language processing, providing capabilities that go far beyond sentence completion including question answering, summarization, and natural-language inference. While many of these capabilities have potential application to cognitive systems, exploiting language models as a source of task knowledge, especially for task learning, offers significant, near-term benefits. We introduce language models and the various tasks to which they have been applied and then review methods of knowledge extraction from language models. The resulting analysis outlines both the challenges and opportunities for using language models as a new knowledge source for cognitive systems. It also identifies possible ways to improve knowledge extraction from language models using the capabilities provided by cognitive systems. Central to success will be the ability of a cognitive agent to itself learn an abstract model of the knowledge implicit in the LM as well as methods to extract high-quality knowledge effectively and efficiently. To illustrate, we introduce a hypothetical robot agent and describe how language models could extend its task knowledge and improve its performance and the kinds of knowledge and methods the agent can use to exploit the knowledge within a language model.
Relational representations in reinforcement learning allow for the use of structural information like the presence of objects and relationships between them in the description of value functions. Through this paper, we show that such representations allow for the inclusion of background knowledge that qualitatively describes a state and can be used to design agents that demonstrate learning behavior in domains with large state and actions spaces such as computer games.