Extending%20the%20Soar%20Cognitive%20Architecture

1
Extending the Soar Cognitive Architecture

• John E. Laird
• University of Michigan
• AGI Conference
• March 1, 2008

http//sitemaker.umich.edu/soar/home
2
Extending Soar
Symbolic Long-Term Memories

• Learn from internal rewards
• Reinforcement learning
• Learn facts
• What you know
• Semantic memory
• Learn events and situtations
• What you remember
• Episodic memory
• Basic drives and
• Emotions, feelings, mood
• Non-symbolic reasoning
• Mental imagery
• Learn from regularities
• Spatial and temporal clusters

Procedural
Chunking
Symbolic Short-Term Memory
Decision Procedure
Perception
Action
Body
3
Soar Processing Cycle
Manipulate Visual Imagery Create Motor
Commands Query Semantic, Episodic Memory, Visual
Imagery Perception
4
Theoretical Commitments

• Stayed the Same

• Changed

• Problem Space Computational Model
• Long-term short-term memories
• Associative procedural knowledge
• Fixed decision procedure
• Impasse-driven reasoning
• Incremental, experience-driven learning
• No task-specific modules

• Multiple long-term memories
• Multiple learning mechanisms
• Modality-specific representations processing
• Non-symbolic processing
• Symbol generation (clustering)
• Control (numeric preferences)
• Learning Control (reinforcement learning)
• Intrinsic reward (appraisals)
• Aid memory retrieval (WM activation)
• Non-symbolic reasoning (visual imagery)

5
Upcoming Challenges

• Continued refinement and integration
• Integrate with complex perception and motor
  systems
• Adding/learning lots of world knowledge
• Language, Spatial, Temporal Reasoning,
• Scaling up to large bodies of knowledge

6
Thanks to

• Funding Agencies
• NSF, DARPA, ONR
• Ph.D. students
• Nate Derbinsky, Nicholas Gorski, Scott Lathrop,
  Robert Marinier, Andrew Nuxoll, Yongjia Wang,
  Samuel Wintermute, Joseph Xu
• Research Programmers
• Karen Coulter, Jonathan Voigt
• Continued inspiration
• Allen Newell