SOAR A cognitive architecture By: Majid Ali Khan.

Slides:



Advertisements
Similar presentations
Pat Langley Computational Learning Laboratory Center for the Study of Language and Information Stanford University, Stanford, California
Advertisements

Pat Langley Arizona State University and Institute for the Study of Learning and Expertise Expertise, Transfer, and Innovation in.
Pat Langley School of Computing and Informatics Arizona State University Tempe, Arizona USA Mental Simulation and Learning in the I CARUS Architecture.
Pat Langley School of Computing and Informatics Arizona State University Tempe, Arizona USA Modeling Social Cognition in a Unified Cognitive Architecture.
Pat Langley School of Computing and Informatics Arizona State University Tempe, Arizona USA A Unified Cognitive Architecture for Embodied Agents Thanks.
Learning To Use Memory Nick Gorski & John Laird Soar Workshop 2011.
ARCHITECTURES FOR ARTIFICIAL INTELLIGENCE SYSTEMS
A Cognitive Architecture Theory of Comprehension and Appraisal: Unifying Cognitive Functions and Appraisal Bob Marinier John Laird University of Michigan.
1 Update on Learning By Observation Learning from Positive Examples Only Tolga Konik University of Michigan.
Introducing Constrained Heuristic Search to the Soar Cognitive Architecture (demonstrating domain independent learning in Soar) The Second Conference on.
Chapter Five The Cognitive Approach II: Memory, Imagery, and Problem Solving.
The CLARION Cognitive Architecture: A Tutorial Part 5 – Conclusion Nick Wilson, Michael Lynch, Ron Sun, Sébastien Hélie Cognitive Science, Rensselaer Polytechnic.
Outline Introduction Soar (State operator and result) Architecture
Introduction to SOAR Based on “a gentle introduction to soar: an Architecture for Human Cognition” by Jill Fain Lehman, John Laird, Paul Rosenbloom. Presented.
Outcome: Project teams will be able to  Identify opportunities and issues for Task-oriented transformations  Commence work on the Task-oriented section.
Artificial Intelligence and Lisp #2 Introduction to Cognitive Agents and to Knowledge Representation.
1 Chunking with Confidence John Laird University of Michigan June 17, th Soar Workshop
Impact of Working Memory Activation on Agent Design John Laird, University of Michigan 1.
1 Soar Semantic Memory Yongjia Wang University of Michigan.
The Importance of Architecture for Achieving Human-level AI John Laird University of Michigan June 17, th Soar Workshop
Cognitive Processes PSY 334 Chapter 8 – Problem Solving May 21, 2003.
A Soar’s Eye View of ACT-R John Laird 24 th Soar Workshop June 11, 2004.
MICHAEL T. COX UMIACS, UNIVERSITY OF MARYLAND, COLLEGE PARK Toward an Integrated Metacognitive Architecture Cox – 8 July 2011.
Polyscheme John Laird February 21, Major Observations Polyscheme is a FRAMEWORK not an architecture – Explicitly does not commit to specific primitives.
Models of Human Performance Dr. Chris Baber. 2 Objectives Introduce theory-based models for predicting human performance Introduce competence-based models.
Reinforcement Learning and Soar Shelley Nason. Reinforcement Learning Reinforcement learning: Learning how to act so as to maximize the expected cumulative.
1 Problem Solving We view many situations in life as problems we need to solve Also, much of human behavior can be considered problem solving, even if.
COMPUTATIONAL MODELING OF INTEGRATED COGNITION AND EMOTION Bob MarinierUniversity of Michigan.
THEORIES OF MIND: AN INTRODUCTION TO COGNITIVE SCIENCE Jay Friedenberg and Gordon Silverman.
FH Augsburg - FB Informatik 1 CADUI' June FUNDP Namur Software Life Cycle Automation for Interactive Applications: The AME Design Environment.
Cognitive development 14 th December Developmental psychology  study of progressive changes in human traits and abilities that occur throughout.
Knowledge Representation and Reasoning University "Politehnica" of Bucharest Department of Computer Science Fall 2010 Adina Magda Florea
Modeling meditation ?! Marieke van Vugt.
Artificial Intelligence Introductory Lecture Jennifer J. Burg Department of Mathematics and Computer Science.
Second Generation ES1 Second Generation Expert Systems Ahme Rafea CS Dept., AUC.
Learning Theories with Technology Learning Theories with Technology By: Jessica Rubinstein.
Integrating Background Knowledge and Reinforcement Learning for Action Selection John E. Laird Nate Derbinsky Miller Tinkerhess.
Bob Marinier Advisor: John Laird Functional Contributions of Emotion to Artificial Intelligence.
WHS AP Psychology Unit 6: Cognition Essential Task 6-2: Identify problem-solving techniques (algorithms and heuristics) as well as factors that influence.
Andreas Wendemuth, Otto-von-Guericke-Universität Magdeburg, SOAR Prof. Dr. Andreas Wendemuth Lehrstuhl Kognitive Systeme / Sprachverarbeitung.
Chapter Five The Cognitive Approach II: Memory, Imagery, and Problem Solving.
CHAPTER FIVE The Cognitive Approach II: Memory, Imagery, and Problem Solving.
Bloom & Gagnè Theories of Learning Bloom & Gagnè Theories of Learning
Spring 2011 Tutor Training Modern Learning Theories and Tutoring Designed and Presented by Tem Fuller.
Soar: An Architecture for Human Behavior Representation
TEACHER INTRODUCTION B.Sc. M.ed.  Physics  Biology to class 9 th and 10 th.
CONSTRUCTIVISM A Model for Designing Constructivist Learning Environments.
RULES Patty Nordstrom Hien Nguyen. "Cognitive Skills are Realized by Production Rules"
Beyond Chunking: Learning in Soar March 22, 2003 John E. Laird Shelley Nason, Andrew Nuxoll and a cast of many others University of Michigan.
Soar Expert System Tools Team W09 Daniel Nelson, Emily Schwarz, and Sean Lydon.
1 Learning through Interactive Behavior Specifications Tolga Konik CSLI, Stanford University Douglas Pearson Three Penny Software John Laird University.
AGI-09 Scott Lathrop John Laird 1. 2  Cognitive Architectures Amodal, symbolic representations & computations No general reasoning with perceptual-based.
Cognitive Architectures and General Intelligent Systems Pay Langley 2006 Presentation : Suwang Jang.
Pat Langley Computational Learning Laboratory Center for the Study of Language and Information Stanford University, Stanford, CA
Strategic Approximation of Human Algorithms: a Request for Comments on a Thesis Ryan Kaulakis Applied Cognitive.
3/14/20161 SOAR CIS 479/579 Bruce R. Maxim UM-Dearborn.
Learning Procedural Knowledge through Observation -Michael van Lent, John E. Laird – 인터넷 기술 전공 022ITI02 성유진.
Cognitive Modeling Cogs 4961, Cogs 6967 Psyc 4510 CSCI 4960 Mike Schoelles
Knowledge Representation and Reasoning
Learning Fast and Slow John E. Laird
Artificial Intelligence and Lisp #2
Social Cognition Aggression
Learning With Information Technology
Knowledge Representation and Reasoning
John E. Laird 32nd Soar Workshop
DoDAF 2.x Meta Model (DM2) Conceptual Level
SOAR as a Cognitive Architecture for Modeling Driver Workload
Cognitive Processes PSY 334
SOAR 1/18/2019.
= 4 = 2 Task 2: Shapes for numbers Build-up part 1
Presentation transcript:

SOAR A cognitive architecture By: Majid Ali Khan

Introduction What does SOAR stand for? What does SOAR stand for? State State Operator Operator And And Result Result An architecture for constructing cognitive models An architecture for constructing cognitive models

Introduction Problem spaces as a single framework for all tasks and subtasks to be solved Problem spaces as a single framework for all tasks and subtasks to be solved Production rules for representation of permanent knowledge Production rules for representation of permanent knowledge Objects with attributes and values for representation of temporary knowledge Objects with attributes and values for representation of temporary knowledge Automatic subgoaling mechanism for generating goals Automatic subgoaling mechanism for generating goals Chunking as learning mechanism Chunking as learning mechanism

High Level Architecture

Rule Memory (permanent)

Working Memory (temporary)

Default Working Memory

HelloWorld Rule

Design Principle The design of Soar is based on the hypothesis that all deliberate goal -oriented behavior can be cast as the selection and application of operators to a state. The design of Soar is based on the hypothesis that all deliberate goal -oriented behavior can be cast as the selection and application of operators to a state. A state is a representation of the current problem-solving situation; an operator transforms a state (makes changes to the representation); and a goal is a desired outcome of the problem-solving activity A state is a representation of the current problem-solving situation; an operator transforms a state (makes changes to the representation); and a goal is a desired outcome of the problem-solving activity

Operational Cycle

Propose Rule

Apply Rule

References SOAR website SOAR website SOAR Tutorial ** SOAR Tutorial ** SOAR FAQ SOAR FAQ SOAR Demo: bremen.de/teaching/cognitive-systems2/Soar_demo.ppt SOAR Demo: bremen.de/teaching/cognitive-systems2/Soar_demo.ppthttp:// bremen.de/teaching/cognitive-systems2/Soar_demo.ppthttp:// bremen.de/teaching/cognitive-systems2/Soar_demo.ppt John Laird Research Activity *: John Laird Research Activity *:

Demo