This paper proposes that the “right” abstraction for representing general intelligence depends on the timescale of behavior under study (Newell 1990) and overall goals of the research – is it to faithfully model the brain, the mind, or to achieve the same functionality? I briefly describe my approach, which focuses on functionality and time scales above .1 seconds. My strategy is to draw inspiration from neuroscience and cognitive psychology to achieve general intelligence through the study and development of the Soar symbolic cognitive architecture.

In this paper, we describe a complex Soar agent that uses and learns multiple types of knowledge while interacting with a human in a real-world domain. Our hypothesis is that a diverse set of memories is required for the different types of knowledge. We first present the agent’s processing, highlighting the types of knowledge used for each phase. We then present Soar’s memories and identify which memory is used for each type of knowledge. We also analyze which properties of each memory make it appropriate for the knowledge it encodes. We conclude with a summary of our analysis.

Our long-term goal is to develop autonomous robotic systems that have the cognitive abilities of humans, including communication, coordination, adapting to novel situations, and learning through experience. Our approach rests on the integration of the Soar cognitive architecture with both virtual and physical robotic systems. Soar has been used to develop a wide variety of knowledge-rich agents for complex virtual environments, including distributed training environments and interactive computer games. For development and testing in robotic virtual environments, Soar interfaces to a variety of robotic simulators and a simple mobile robot. We have recently made significant extensions to Soar that add new memories and new non-symbolic reasoning to Soar’s original symbolic processing, which improves Soar abilities for control of robots. These extensions include mental imagery, episodic and semantic memory, reinforcement learning, and continuous model learning. This paper presents research in mobile robotics, relational and continuous model learning, and learning by situated, interactive instruction.

One challenge for cognitive architectures is to effectively use different forms of knowledge and learning. We present a case study of Soar agents that play a multiplayer dice game, in which probabilistic reasoning and heuristic symbolic knowledge appear to play a central role. We develop and evaluate a collection of agents that use different combinations of probabilistic decision making, heuristic symbolic reasoning, opponent modeling, and learning. We demonstrate agents that use Soar’s rule learning mechanism (chunking) to convert deliberate reasoning with probabilities into implicit reasoning, and then use reinforcement learning to further tune performance.