38 citations · 89 across the 12 of their papers we have counts for
12 papers
Acquiring Grounded Representations of Words with Situated Interactive Instruction
Shiwali Mohan, Aaron H. Mininger, James R. Kirk +1
We present an approach for acquiring grounded representations of words from mixed-initiative, situated interactions with a human instructor. The work focuses on the acquisition of…
Computational-level Analysis of Constraint Compliance for General Intelligence
Robert E. Wray, Steven J. Jones, John E. Laird
Human behavior is conditioned by codes and norms that constrain action. Rules, ``manners,'' laws, and moral imperatives are examples of classes of constraints that govern human beh…
Improving Language Model Prompting in Support of Semi-autonomous Task Learning
James R. Kirk, Robert E. Wray, Peter Lindes +1
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…
Integrating Diverse Knowledge Sources for Online One-shot Learning of Novel Tasks
James R. Kirk, Robert E. Wray, Peter Lindes +1
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…
Introduction to Soar
John E. Laird
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…
An Analysis and Comparison of ACT-R and Soar
John E. Laird
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 t…
Language Models as a Knowledge Source for Cognitive Agents
Robert E. Wray, III, James R. Kirk +1
Language models (LMs) are sentence-completion engines trained on massive corpora. LMs have emerged as a significant breakthrough in natural-language processing, providing capabilit…
A Computational Model for Situated Task Learning with Interactive Instruction
Shiwali Mohan, James Kirk, John Laird
Learning novel tasks is a complex cognitive activity requiring the learner to acquire diverse declarative and procedural knowledge. Prior ACT-R models of acquiring task knowledge f…
Towards an Indexical Model of Situated Language Comprehension for Cognitive Agents in Physical Worlds
Shiwali Mohan, Aaron Mininger, John Laird
We propose a computational model of situated language comprehension based on the Indexical Hypothesis that generates meaning representations by translating amodal linguistic symbol…
Relational Reinforcement Learning in Infinite Mario
Shiwali Mohan, John E. Laird
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 v…
An Architectural Approach to Ensuring Consistency in Hierarchical Execution
J. E. Laird, R. E. Wray
Hierarchical task decomposition is a method used in many agent systems to organize agent knowledge. This work shows how the combination of a hierarchy and persistent assertions of…
Flexibly Instructable Agents
S. B. Huffman, J. E. Laird
This paper presents an approach to learning from situated, interactive tutorial instruction within an ongoing agent. Tutorial instruction is a flexible (and thus powerful) paradigm…