Much of the work in machine learning has focused on demonstrating the efficacy of learning techniques using training and testing phases. On-line learning over the long term places different demands on symbolic machine learning techniques and raises a different set of questions for symbolic learning than for empirical learning. We have instrumented Soar to collect data and characterize the long-...

Cognitive architecture's purpose is to generate artificial agents with capacities similar the human mind. Soar Architecture produce fixed computational building blocks needed for generally intelligent agents— that can outright a variety of tasks and encode, use, learn all types knowledge realize broad cognitive abilities present in humans. This paper introduced an arithmetic agent does multicol...

Eur J Aneasthesiol Suppl 1997;15:17–20 7. Soar SJ, Smith MB, Soar J, Morris PJ. Does glycine antagonism underlie the excitatory effects of propofol and methohexitone? Br J Anaesth 1992;68:523–6 8. Walder B, Tramèr MR, Seem M. Seizurelike phenomena and propofol. A systematic review. Neurology 2002;58:1327–32 9. Wang B, Bai Q, Jiao W, Wang E, White PF. Effect of sedative and hypnotic doses of pro...

Much of the work in machine learning has focused on situations in which there are distinct training and testing phases. However, the recent increase in interest in real-world systems involving scaling up has led to an increased attention to “anytime learning”, i.e., systems in which learning mechanisms are always active. This places different demands on machine learning techniques and raises a ...

Endowing an intelligent agent with an episodic memory affords it a multitude of cognitive capabilities. However, providing efficient storage and retrieval in a task-independent episodic memory presents considerable theoretical and practical challenges. We characterize the computational issues bounding an episodic memory. We explore whether even with intractable asymptotic growth, it is possible...

This paper describes a BDI-inspired abstraction layer that is implemented in Soar to increase the scalability and flexibility of knowledge engineering in Soar-based agent systems. We motivate the BDI abstraction with a specific example of a multi-agent system that is being developed to explore human command and control of heterogeneous robotic entities. We then describe how we have implemented ...

The characteristics of long-term, symbolic learning were investigated using Soar and ACT-R models of a task to rearrange blocks into specific configurations. Long sequences of problems were run collecting data to answer fundamental questions about long-term, symbolic learning. The questions were whether symbolic learning continues indefinitely, how learned knowledge is used, and whether perform...