Soar (cognitive architecture)
Encyclopedia
Soar is a symbolic
cognitive architecture
, created by John Laird
, Allen Newell
, and Paul Rosenbloom at Carnegie Mellon University
, now maintained by John Laird's research group at the University of Michigan
. It is both a view of what cognition
is and an implementation of that view through a computer program
ming architecture for Artificial Intelligence
(AI). Since its beginnings in 1983 and its presentation in a paper in 1987, it has been widely used by AI researchers to model
different aspects of human behavior
.
, from highly routine to extremely difficult open-ended problems. In order for that to happen, according to the view underlying Soar, it needs to be able to create representation
s and use appropriate forms of knowledge (such as procedural
, declarative, episodic). Soar should then address a collection of mechanisms of the mind
. Also underlying the Soar architecture is the view that a symbolic system
is essential for general intelligence (see brief comment on neats versus scruffies
). This is known as the physical symbol system
hypothesis. The views of cognition underlying Soar are tied to the psychological theory expressed in Allen Newell
's book, Unified Theories of Cognition.
While symbol processing remains the core mechanism in the architecture, recent versions of the theory incorporate non-symbolic representations and processes, including reinforcement learning
, imagery processing, and emotion
modeling (Laird, 2008).
Although the ultimate goal for Soar is to achieve general intelligence
, there is no claim that this goal has already been reached. Advocates of the system recognize that Soar is still missing some important aspects of intelligence. Some examples of missing capabilities include automatically creating new representations on its own, such as through hierarchical clustering
.
, i.e. it uses explicit production rules to govern its behavior (these are roughly of the form "if... then...", as also used in expert system
s). Problem solving can be roughly described as a search through a problem space (the collection of different states which can be reached by the system at a particular time) for a goal state (which represents the solution for the problem). This is implemented by searching for the states which bring the system gradually closer to its goal. Each move consists of a decision cycle which has an elaboration phase (in which a variety of different pieces of knowledge bearing the problem are brought to Soar's working memory
) and a decision procedure (which weighs what was found on the previous phase and assigns preferences to ultimately decide the action to be taken). In addition to problem space search, however, Soar can be used to instantiate reasoning techniques such as reinforcement learning
which do not require detailed internal models of the environment. In this way, Soar is flexible to behaving when varying amounts of task knowledge are available.
SOAR originally stood for State, Operator And Result, reflecting this representation of problem solving as the application of an operator to a state to get a result. According to the project FAQ, the Soar development community no longer regards Soar as an acronym so it is no longer spelled all in caps though it is still representative of the core of the implementation.
If the decision procedure just described is not able to determine a unique course of action, Soar may use different strategies, known as weak methods to solve the impasse. These methods are appropriate to situations in which knowledge is not abundant. Some examples are means-ends analysis
(which may calculate the difference between each available option and the goal state) and a type of hill-climbing
. When a solution is found by one of these methods, Soar uses a learning technique called chunking
to transform the course of action taken into a new rule. The new rule can then be applied whenever Soar encounters the situation again (that is, there will no longer be an impasse).
ACT-R
is another cognitive architecture by John R. Anderson that operates on similar principles. Other cognitive architectures are CHREST, CLARION
, ICARUS, DUAL
, and Psi.
Cognitivism (psychology)
In psychology, cognitivism is a theoretical framework for understanding the mind that came into usage in the 1950s. The movement was a response to behaviorism, which cognitivists said neglected to explain cognition...
cognitive architecture
Cognitive architecture
A cognitive architecture is a blueprint for intelligent agents. It proposes computational processes that act like certain cognitive systems, most often, like a person, or acts intelligent under some definition. Cognitive architectures form a subset of general agent architectures...
, created by John Laird
John E. Laird
John E. Laird is a computer scientist who, with Paul Rosenbloom and Allen Newell, created the Soar cognitive architecture at Carnegie Mellon University. Laird is a Professor of the Computer Science and Engineering Division of the Electrical Engineering and Computer Science Department of the...
, Allen Newell
Allen Newell
Allen Newell was a researcher in computer science and cognitive psychology at the RAND corporation and at Carnegie Mellon University’s School of Computer Science, Tepper School of Business, and Department of Psychology...
, and Paul Rosenbloom at Carnegie Mellon University
Carnegie Mellon University
Carnegie Mellon University is a private research university in Pittsburgh, Pennsylvania, United States....
, now maintained by John Laird's research group at the University of Michigan
University of Michigan
The University of Michigan is a public research university located in Ann Arbor, Michigan in the United States. It is the state's oldest university and the flagship campus of the University of Michigan...
. It is both a view of what cognition
Cognition
In science, cognition refers to mental processes. These processes include attention, remembering, producing and understanding language, solving problems, and making decisions. Cognition is studied in various disciplines such as psychology, philosophy, linguistics, and computer science...
is and an implementation of that view through a computer program
Computer program
A computer program is a sequence of instructions written to perform a specified task with a computer. A computer requires programs to function, typically executing the program's instructions in a central processor. The program has an executable form that the computer can use directly to execute...
ming architecture for Artificial Intelligence
Artificial intelligence
Artificial intelligence is the intelligence of machines and the branch of computer science that aims to create it. AI textbooks define the field as "the study and design of intelligent agents" where an intelligent agent is a system that perceives its environment and takes actions that maximize its...
(AI). Since its beginnings in 1983 and its presentation in a paper in 1987, it has been widely used by AI researchers to model
Cognitive model
A cognitive model is an approximation to animal cognitive processes for the purposes of comprehension and prediction. Cognitive models can be developed within or without a cognitive architecture, though the two are not always easily distinguishable.In contrast to cognitive architectures, cognitive...
different aspects of human behavior
Human behavior
Human behavior refers to the range of behaviors exhibited by humans and which are influenced by culture, attitudes, emotions, values, ethics, authority, rapport, hypnosis, persuasion, coercion and/or genetics....
.
Theory
The main goal of the Soar project is to be able to handle the full range of capabilities of an intelligent agentIntelligent agent
In artificial intelligence, an intelligent agent is an autonomous entity which observes through sensors and acts upon an environment using actuators and directs its activity towards achieving goals . Intelligent agents may also learn or use knowledge to achieve their goals...
, from highly routine to extremely difficult open-ended problems. In order for that to happen, according to the view underlying Soar, it needs to be able to create representation
Knowledge representation
Knowledge representation is an area of artificial intelligence research aimed at representing knowledge in symbols to facilitate inferencing from those knowledge elements, creating new elements of knowledge...
s and use appropriate forms of knowledge (such as procedural
Procedural knowledge
Procedural knowledge, also known as imperative knowledge, is the knowledge exercised in the performance of some task. See below for the specific meaning of this term in cognitive psychology and intellectual property law....
, declarative, episodic). Soar should then address a collection of mechanisms of the mind
Mind
The concept of mind is understood in many different ways by many different traditions, ranging from panpsychism and animism to traditional and organized religious views, as well as secular and materialist philosophies. Most agree that minds are constituted by conscious experience and intelligent...
. Also underlying the Soar architecture is the view that a symbolic system
Symbolic system
In the fields of anthropology, sociology, and psychology, symbolic system refers to a system of interconnected symbolic meanings. In particular, the field focuses on the dynamic relationships between various symbols within different task or theoretical contexts...
is essential for general intelligence (see brief comment on neats versus scruffies
Neats vs. scruffies
Neat and scruffy are labels for two different types of artificial intelligence research. Neats consider that solutions should be elegant, clear and provably correct...
). This is known as the physical symbol system
Physical symbol system
A physical symbol system takes physical patterns , combining them into structures and manipulating them to produce new expressions....
hypothesis. The views of cognition underlying Soar are tied to the psychological theory expressed in Allen Newell
Allen Newell
Allen Newell was a researcher in computer science and cognitive psychology at the RAND corporation and at Carnegie Mellon University’s School of Computer Science, Tepper School of Business, and Department of Psychology...
's book, Unified Theories of Cognition.
While symbol processing remains the core mechanism in the architecture, recent versions of the theory incorporate non-symbolic representations and processes, including reinforcement learning
Reinforcement learning
Inspired by behaviorist psychology, reinforcement learning is an area of machine learning in computer science, concerned with how an agent ought to take actions in an environment so as to maximize some notion of cumulative reward...
, imagery processing, and emotion
Emotion
Emotion is a complex psychophysiological experience of an individual's state of mind as interacting with biochemical and environmental influences. In humans, emotion fundamentally involves "physiological arousal, expressive behaviors, and conscious experience." Emotion is associated with mood,...
modeling (Laird, 2008).
Although the ultimate goal for Soar is to achieve general intelligence
Strong AI
Strong AI is artificial intelligence that matches or exceeds human intelligence — the intelligence of a machine that can successfully perform any intellectual task that a human being can. It is a primary goal of artificial intelligence research and an important topic for science fiction writers and...
, there is no claim that this goal has already been reached. Advocates of the system recognize that Soar is still missing some important aspects of intelligence. Some examples of missing capabilities include automatically creating new representations on its own, such as through hierarchical clustering
Hierarchical clustering
In statistics, hierarchical clustering is a method of cluster analysis which seeks to build a hierarchy of clusters. Strategies for hierarchical clustering generally fall into two types:...
.
Architecture
Soar is based on a production systemProduction system
A production system is a computer program typically used to provide some form of artificial intelligence, which consists primarily of a set of rules about behavior. These rules, termed productions, are a basic representation found useful in automated planning, expert systems and action selection...
, i.e. it uses explicit production rules to govern its behavior (these are roughly of the form "if... then...", as also used in expert system
Expert system
In artificial intelligence, an expert system is a computer system that emulates the decision-making ability of a human expert. Expert systems are designed to solve complex problems by reasoning about knowledge, like an expert, and not by following the procedure of a developer as is the case in...
s). Problem solving can be roughly described as a search through a problem space (the collection of different states which can be reached by the system at a particular time) for a goal state (which represents the solution for the problem). This is implemented by searching for the states which bring the system gradually closer to its goal. Each move consists of a decision cycle which has an elaboration phase (in which a variety of different pieces of knowledge bearing the problem are brought to Soar's working memory
Working memory
Working memory has been defined as the system which actively holds information in the mind to do verbal and nonverbal tasks such as reasoning and comprehension, and to make it available for further information processing...
) and a decision procedure (which weighs what was found on the previous phase and assigns preferences to ultimately decide the action to be taken). In addition to problem space search, however, Soar can be used to instantiate reasoning techniques such as reinforcement learning
Reinforcement learning
Inspired by behaviorist psychology, reinforcement learning is an area of machine learning in computer science, concerned with how an agent ought to take actions in an environment so as to maximize some notion of cumulative reward...
which do not require detailed internal models of the environment. In this way, Soar is flexible to behaving when varying amounts of task knowledge are available.
SOAR originally stood for State, Operator And Result, reflecting this representation of problem solving as the application of an operator to a state to get a result. According to the project FAQ, the Soar development community no longer regards Soar as an acronym so it is no longer spelled all in caps though it is still representative of the core of the implementation.
If the decision procedure just described is not able to determine a unique course of action, Soar may use different strategies, known as weak methods to solve the impasse. These methods are appropriate to situations in which knowledge is not abundant. Some examples are means-ends analysis
Means-ends analysis
Means-Ends Analysis is a technique used in Artificial Intelligence for controlling search in problem solving computer programs.It is also a technique used at least since the 1950s as a creativity tool, most frequently mentioned in engineering books on design methods...
(which may calculate the difference between each available option and the goal state) and a type of hill-climbing
Optimization (computer science)
In computer science, program optimization or software optimization is the process of modifying a software system to make some aspect of it work more efficiently or use fewer resources...
. When a solution is found by one of these methods, Soar uses a learning technique called chunking
Chunking (psychology)
Chunking, in psychology, is a phenomenon whereby individuals group responses when performing a memory task. Tests where individuals can illustrate "chunking" commonly include serial and free recall, as these both require the individual to reproduce items that he or she had previously been...
to transform the course of action taken into a new rule. The new rule can then be applied whenever Soar encounters the situation again (that is, there will no longer be an impasse).
ACT-R
ACT-R
ACT-R is a cognitive architecture mainly developed by John Robert Anderson at Carnegie Mellon University. Like any cognitive architecture, ACT-R aims to define the basic and irreducible cognitive and perceptual operations that enable the human mind....
is another cognitive architecture by John R. Anderson that operates on similar principles. Other cognitive architectures are CHREST, CLARION
CLARION (cognitive architecture)
Connectionist Learning with Adaptive Rule Induction ON-line is a cognitive architecture that incorporates the distinction between implicit and explicit processes and focuses on capturing the interaction between these two types of processes. By focusing on this distinction, CLARION has been used to...
, ICARUS, DUAL
DUAL (cognitive architecture)
DUAL is a general cognitive architecture integrating the connectionist and symbolic approaches at the micro level. DUAL is based on decentralized representation and emergent computation. It was inspired by the Society of Mind idea proposed by Marvin Minsky but departs from the initial proposal in...
, and Psi.
See also
- Belief-Desire-Intention software model (BDI software agent)
- CycCycCyc is an artificial intelligence project that attempts to assemble a comprehensive ontology and knowledge base of everyday common sense knowledge, with the goal of enabling AI applications to perform human-like reasoning....
- OpenCogOpenCogOpenCog is a project that aims to build an open source artificial general intelligence framework. OpenCog Prime is a specific set of interacting components designed to give rise to human-equivalent artificial general intelligence...