Soar is a

cognitive architecture A cognitive architecture refers to both a theory about the structure of the human mind and to a computational instantiation of such a theory used in the fields of artificial intelligence (AI) and computational cognitive science. The formalized mod ...

, originally created by John Laird, Allen Newell, and

Paul Rosenbloom Paul may refer to: *Paul (given name), a given name (includes a list of people with that name) * Paul (surname), a list of people People Christianity *Paul the Apostle (AD c.5–c.64/65), also known as Saul of Tarsus or Saint Paul, early Chri ...

at Carnegie Mellon University. (Rosenbloom continued to serve as co-principal investigator after moving to Stanford University, then to the

University of Southern California , mottoeng = "Let whoever earns the palm bear it" , religious_affiliation = Nonsectarian—historically Methodist , established = , accreditation = WSCUC , type = Private research university , academic_affiliations = , endowment = $8.1 ...

's Information Sciences Institute.) It is no
maintained and developed
by John Laird's research group at the

University of Michigan , mottoeng = "Arts, Knowledge, Truth" , former_names = Catholepistemiad, or University of Michigania (1817–1821) , budget = $10.3 billion (2021) , endowment = $17 billion (2021)As o ...

. The goal of the Soar project is to develop the fixed computational building blocks necessary for general

intelligent agent In artificial intelligence, an intelligent agent (IA) is anything which perceives its environment, takes actions autonomously in order to achieve goals, and may improve its performance with learning or may use knowledge. They may be simple or ...

s – agents that can perform a wide range of tasks and encode, use, and learn all types of knowledge to realize the full range of cognitive capabilities found in humans, such as decision making, problem solving, planning, and natural-language understanding. It is both a theory of what cognition is and a computational implementation of that theory. Since its beginnings in 1983 as John Laird’s thesis, it has been widely used by AI researchers to create intelligent agents and

cognitive model A cognitive model is an approximation of one or more cognitive processes in humans or other animals for the purposes of comprehension and prediction. There are many types of cognitive models, and they can range from box-and-arrow diagrams to a set ...

s of different aspects of

human behavior Human behavior is the potential and expressed capacity ( mentally, physically, and socially) of human individuals or groups to respond to internal and external stimuli throughout their life. Kagan, Jerome, Marc H. Bornstein, and Richard M. ...

. The most current and comprehensive description of Soar is the 2012 book, ''The Soar Cognitive Architecture.''

Theory

Soar embodies multiple hypotheses about the computational structures underlying

general intelligence The ''g'' factor (also known as general intelligence, general mental ability or general intelligence factor) is a construct developed in psychometric investigations of cognitive abilities and human intelligence. It is a variable that summarizes ...

, many of which are shared with other cognitive architectures, including

ACT-R ACT-R (pronounced /ˌækt ˈɑr/; short for "Adaptive Control of Thought—Rational") is a cognitive architecture mainly developed by John Robert Anderson and Christian Lebiere at Carnegie Mellon University. Like any cognitive architecture, ACT-R ...

, which was created by John R. Anderson, and

LIDA Lida ( be, Лі́да ; russian: Ли́да ; lt, Lyda; lv, Ļida; pl, Lida ; yi, לידע, Lyde) is a city 168 km (104 mi) west of Minsk in western Belarus in Grodno Region. Etymology The name ''Lida'' arises from its Lithuan ...

, which was created by

Stan Franklin Stan Franklin (born August 14, 1931) is an American scientist. He is the W. Harry Feinstone Interdisciplinary Research Professor at the University of Memphis in Memphis, Tennessee, and co-director of the Institute of Intelligent Systems.Shepar ...

. Recently, the emphasis on Soar has been on general AI (functionality and efficiency), whereas the emphasis on ACT-R has always been on

ing (detailed modeling of human cognition). The original theory of cognition underlying Soar is the Problem Space Hypothesis, which is described in Allen Newell's book, '' Unified Theories of Cognition''. and dates back to one of the first AI systems created, Newell,

Simon Simon may refer to: People * Simon (given name), including a list of people and fictional characters with the given name Simon * Simon (surname), including a list of people with the surname Simon * Eugène Simon, French naturalist and the genus ...

, and Shaw's

Logic Theorist Logic Theorist is a computer program written in 1956 by Allen Newell, Herbert A. Simon, and Cliff Shaw. , and It was the first program deliberately engineered to perform automated reasoning and is called "the first artificial intelligence prog ...

, first presented in 1955. The Problem Space Hypothesis contends that all goal-oriented behavior can be cast as search through a space of possible states (a ''problem space'') while attempting to achieve a goal. At each step, a single operator is selected, and then applied to the agent’s current state, which can lead to internal changes, such as retrieval of knowledge from long-term memory or modifications or external actions in the world. (Soar’s name is derived from this basic cycle of State, Operator, And Result; however, it is no longer regarded as an acronym.) Inherent to the Problem Space Hypothesis is that all behavior, even a complex activity such as planning, is decomposable into a sequence of selection and application of primitive operators, which when mapped onto human behavior take ~50ms. A second hypothesis of Soar’s theory is that although only a single operator can be selected at each step, forcing a serial bottleneck, the processes of selection and application are implemented through parallel rule firings, which provide context-dependent retrieval of procedural knowledge. A third hypothesis is that if the knowledge to select or apply an operator is incomplete or uncertain, an impasse arises and the architecture automatically creates a substate. In the substate, the same process of problem solving is recursively used, but with the goal to retrieve or discover knowledge so that decision making can continue. This can lead to a stack of substates, where traditional problem methods, such as planning or hierarchical task decomposition, naturally arise. When results created in the substate resolve the impasse, the substate and its associated structures are removed. The overall approach is called Universal Subgoaling. These assumptions lead to an architecture that supports three levels of processing. At the lowest level, is bottom-up, parallel, and automatic processing. The next level is the deliberative level, where knowledge from the first level is used to propose, select, and apply a single action. These two levels implement fast, skilled behavior, and roughly correspond to Kahneman’s System 1 processing level. More complex behavior arises automatically when knowledge is incomplete or uncertain, through a third level of processing using substates, roughly corresponding to System 2. A fourth hypothesis in Soar is that the underlying structure is modular, but not in terms of task or capability based modules, such as planning or language, but instead as task independent modules including: a decision making module; memory modules (short-term spatial/visual and working memories; long-term procedural, declarative, and episodic memories), learning mechanisms associated with all long-term memories; and perceptual and motor modules. There are further assumptions about the specific properties of these memories described below, including that all learning is online and incremental. A fifth hypothesis is that memory elements (except those in the spatial/visual memory) are represented as symbolic, relational structures. The hypothesis that a symbolic system is necessary for general

intelligence Intelligence has been defined in many ways: the capacity for abstraction, logic, understanding, self-awareness, learning, emotional knowledge, reasoning, planning, creativity, critical thinking, and problem-solving. More generally, it can be des ...

is known as the '' physical symbol system hypothesis''. An important evolution in Soar is that all symbolic structures have associated statistical metadata (such as information on recency and frequency of use, or expected future reward) that influences retrieval, maintenance, and learning of the symbolic structures.

Architecture

Processing cycle – decision procedure

Soar’s main processing cycle arises from the interaction between procedural memory (its knowledge about how to do things) and

working memory Working memory is a cognitive system with a limited capacity that can hold information temporarily. It is important for reasoning and the guidance of decision-making and behavior. Working memory is often used synonymously with short-term memory, ...

(its representation of the current situation) to support the selection and application of operators. Information in working memory is represented as a symbolic graph structure, rooted in a ''state.'' The knowledge in procedural memory is represented as if-then

rules Rule or ruling may refer to: Education * Royal University of Law and Economics (RULE), a university in Cambodia Human activity * The exercise of political or personal control by someone with authority or power * Business rule, a rule pert ...

(sets of conditions and actions), that are continually matched against the contents of working memory. When the conditions of a rule matches structures in working memory, it ''fires'' and performs its actions. This combination of rules and working memory is also called a production system. In contrast to most production systems, in Soar, all rules that match, fire in parallel. Instead of having the selection of a single rule being the crux of decision making, Soar’s decision making occurs through the selection and applications of ''operators'', that are proposed, evaluated, and applied by rules. An operator is proposed by rules that test the current state and create a representation of the operator in working memory as well as an ''acceptable preference'', which indicates that the operator should be considered for selection and application. Additional rules match with the proposed operator and create additional preferences that compare and evaluate it against other proposed operators. The preferences are analyzed by a decision procedure, which selects the preferred operator and installs it as the current operator in working memory. Rules that match the current operator then fire to apply it and make changes to working memory. The changes to working memory can be simple inferences, queries for retrieval from Soar’s long-term semantic or episodic memories, commands to the motor system to perform actions in an environment, or interactions with the Spatial Visual System (SVS), which is working memory’s interface to perception. These changes to working memory lead to new operators being proposed and evaluated, followed by the selection of one and its application.

Reinforcement learning

Soar supports

reinforcement learning Reinforcement learning (RL) is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward. Reinforcement learning is one of three basic machine ...

, which tunes the values of rules that create numeric preferences for evaluating operators, based on reward. To provide maximal flexibility, there is a structure in working memory where reward is created.

Impasses, substates, and chunking

If the preferences for the operators are insufficient to specify the selection of a single operator, or there are insufficient rules to apply an operator, an impasse arises. In response to an impasse, a substate is created in working memory, with the goal being to resolve the impasse. Additional procedural knowledge can then propose and select operators in the substate to gain more knowledge, and either create preferences in the original state or modify that state so the impasse is resolved. Substates provide a means for on-demand complex reasoning, including hierarchical task decomposition, planning, and access to the declarative long-term memories. Once the impasse is resolved, all of the structures in the substate are removed except for any results. Soar’s chunking mechanism compiles the processing in the substate which led to results into rules. In the future, the learned rules automatically fire in similar situations so that no impasse arises, incrementally converting complex reasoning into automatic/reactive processing. Recently, the overall Universal Subgoaling procedure has been extended through a mechanism of goal-directed and automatic knowledge base augmentation that allows to solve an impasse by recombining, in an innovative and problem-oriented way, the knowledge possessed by a Soar agent.

Symbolic input and output

Symbolic input and output occurs through working memory structures attached to the top state called the input-link and the output-link. If structures are created on the output-link in working memory, these are translated into commands for external actions (e.g., motor control).

Spatial visual system and mental imagery

To support interaction with vision systems and non-symbolic reasoning, Soar has its Spatial Visual System (SVS). SVS internally represents the world as a ''scene graph'', a collection of objects and component subobjects each with spatial properties such as shape, location, pose, relative position, and scale. A Soar agent using SVS can create filters to automatically extract features and relations from its scene graph, which are then added to working memory. In addition, a Soar agent can add structures to SVS and use it for mental imagery. For example, an agent can create a hypothetical object in SVS at a given location and query to see if it collides with any perceived objects.

Semantic memory

Semantic Memory Semantic memory refers to general world knowledge that humans have accumulated throughout their lives. This general knowledge (word meanings, concepts, facts, and ideas) is intertwined in experience and dependent on culture. We can learn about n ...

(SMEM) in Soar is designed to be a very large long-term memory of fact-like structures. Data in SMEM is represented as directed cyclic graphs. Structures can be stored or retrieved by rules that create commands in a reserved area of working memory. Retrieved structures are added to working memory. SMEM structures have activation values that represent the frequency or recency of usage of each memory, implementing the ''base-level activation'' scheme originally developed for ACT-R. During retrieval, the structure in SMEM that matches the query and has the highest activation is retrieved. Soar also supports '' spreading activation'', where activation spreads from SMEM structures that have been retrieved into working memory to other long-term memories that they are linked to. These memories in turn spread activation to their neighbor memories, with some decay. Spreading activation is a mechanism for allowing the current context to influence retrievals from semantic memory.

Episodic memory

Episodic Memory Episodic memory is the memory of everyday events (such as times, location geography, associated emotions, and other contextual information) that can be explicitly stated or conjured. It is the collection of past personal experiences that occurred ...

(EPMEM) automatically records snapshots of working memory in a temporal stream. Prior episodes can be retrieved into working memory through query. Once an episode has been retrieved, the next (or previous) episode can then be retrieved. An agent may employ EPMEM to sequentially play through episodes from its past (allowing it to predict the effects of actions), retrieve specific memories, or query for episodes possessing certain memory structures.

Learning

Each of Soar’s long-term memories have associated online learning mechanisms that create new structures or modify metadata based on an agent’s experience. For example, Soar learns new rules for procedural memory through a process called ''chunking'' and uses reinforcement learning to tune rules involved in the selection of operators.

Agent development

The standard approach to developing an agent in Soar starts with writing rules that are loaded into procedural memory, and initializing semantic memory with appropriate declarative knowledge. The process of agent development is explained in detail in the official Soar manual as well as in several tutorials which are provided at the research group'
website

Software

Extending the Soar Cognitive Architecture by John Laird of University of Michigan

The Soar architecture is maintained and extended by John Laird's research group at the University of Michigan. The current architecture is written in a combination of C and C++, and is freely available (BSD license) at the research group'
website
Soar can interface with external language environments including C++, Java, Tcl, and Python through the Soar Markup Language (SML). SML is a primary mechanism for creating instances of Soar agents and interacting with their I/O links. JSoar is an implementation of Soar written in Java. It is maintained b
SoarTech
an AI research and development company. JSoar closely follows the University of Michigan architecture implementation, although it generally does not reflect the latest developments and changes of that C/C++ version.

Applications

Below is a historical list of different areas of applications that have been implemented in Soar. There have been over a hundred systems implemented in Soar, although the vast majority of them are toy tasks or puzzles.

Puzzles and games

Throughout its history, Soar has been used to implement a wide variety of classic AI puzzles and games, such as Tower of Hanoi, Water Jug, Tic Tac Toe, Eight Puzzle, Missionaries and Cannibals, and variations of the Blocks world. One of the initial achievements of Soar was showing that many different weak methods would naturally arise from the task knowledge that was encoded in it, a property called, the ''Universal Weak Method.''

Computer configuration

The first large-scale application of Soar was R1-Soar, a partial reimplementation by Paul Rosenbloom of the R1 ( XCON) expert system John McDermott developed for configuring DEC computers. R1-Soar demonstrated the ability of Soar to scale to moderate-size problems, use hierarchical task decomposition and planning, and convert deliberate planning and problem solving to reactive execution through chunking.

Natural-language understanding

NL-Soar was a

natural-language understanding Natural-language understanding (NLU) or natural-language interpretation (NLI) is a subtopic of natural-language processing in artificial intelligence that deals with machine reading comprehension. Natural-language understanding is considered an A ...

system developed in Soar by Jill Fain Lehman, Rick Lewis, Nancy Green, Deryle Lonsdale and Greg Nelson. It included capabilities for natural-language comprehension, generation, and dialogue, emphasizing real-time incremental parsing and generation. NL-Soar was used in an experimental version of TacAir-Soar and in NTD-Soar.

Simulated pilots

The second large-scale application of Soar involved developing agents for use in training in large-scale distributed simulation. Two major systems for flying U.S. tactical air missions were co-developed at the University of Michigan and Information Sciences Institute (ISI) of University of Southern California. The Michigan system was called TacAir-Soar and flew (in simulation)

fixed-wing A fixed-wing aircraft is a heavier-than-air flying machine, such as an airplane, which is capable of flight using wings that generate lift caused by the aircraft's forward airspeed and the shape of the wings. Fixed-wing aircraft are distinct ...

U. S. military tactical missions (such as close-air support, strikes,

CAPs Caps are flat headgear. Caps or CAPS may also refer to: Science and technology Computing * CESG Assisted Products Service, provided by the U.K. Government Communications Headquarters * Composite Application Platform Suite, by Java Caps, a Ja ...

, refueling, and SEAD missions). The ISI system was called RWA-Soar and flew rotary-wing (helicopter) missions. Some of the capabilities incorporated in TacAir-Soar and RWA-Soar were attention, situational awareness and adaptation, real-time planning and dynamic replanning, and complex communication, coordination, and cooperation among combinations of Soar agents and humans. These systems participated in

DARPA The Defense Advanced Research Projects Agency (DARPA) is a research and development agency of the United States Department of Defense responsible for the development of emerging technologies for use by the military. Originally known as the Ad ...

’s Synthetic Theater of War (STOW-97) Advanced Concept Technology Demonstration (ACTD), which at the time was the largest fielding of synthetic agents in a joint battlespace over a 48-hour period, and involved training of active duty personnel. These systems demonstrated the viability of using AI agents for large-scale training.

STEAM

One of the important outgrowths of the RWA-Soar project was the development of STEAM by

Milind Tambe Milind Tambe known as Gordon McKay Professor of Computer Science and Director of Center for Research on Computation and Society at Harvard University; he is also the Director "AI for Social Good" at Google Research India. Career Fellowship ...

, a framework for flexible teamwork in which agents maintained models of their teammates using the joint intentions framework by Cohen & Levesque.

NTD-Soar

NTD-Soar was a simulation of the NASA Test Director (NTD), the person responsible for coordinating the preparation of the

NASA The National Aeronautics and Space Administration (NASA ) is an independent agencies of the United States government, independent agency of the US federal government responsible for the civil List of government space agencies, space program ...

Space Shuttle The Space Shuttle is a retired, partially reusable low Earth orbital spacecraft system operated from 1981 to 2011 by the U.S. National Aeronautics and Space Administration (NASA) as part of the Space Shuttle program. Its official program ...

before launch. It was an integrated cognitive model that incorporated many different complex cognitive capabilities including natural-language processing, attention and visual search, and problem solving in a broad agent model.

Virtual humans

Soar has been used to simulate virtual humans supporting face-to-face dialogues and collaboration within a virtual world developed at the Institute of Creative Technology at USC. Virtual humans have integrated capabilities of

perception Perception () is the organization, identification, and interpretation of sensory information in order to represent and understand the presented information or environment. All perception involves signals that go through the nervous system ...

emotions Emotions are mental states brought on by neurophysiological changes, variously associated with thoughts, feelings, behavioral responses, and a degree of pleasure or displeasure. There is currently no scientific consensus on a definition. ...

, body control, and action, among others.

Game AIs and mobile apps

Game AI agents have been built using Soar for games such as StarCraft,

Quake II ''Quake II'' is a 1997 first-person shooter video game developed by id Software and published by Activision. It is the second installment of the ''Quake'' series, but not a direct sequel to '' Quake''. The game's storyline is continued in its ...

Descent 3 ''Descent 3'' (stylized as ''Descent³'') is a first-person shooter video game developed by Outrage Entertainment and published by Interplay Entertainment. It was originally released for Microsoft Windows in North America on June 17, 1999. ''D ...

Unreal Tournament ''Unreal Tournament'' is a first-person arena shooter video game developed by Epic Games and Digital Extremes. The second installment in the '' Unreal'' series, it was first published by GT Interactive in 1999 for Microsoft Windows, and late ...

, and

Minecraft ''Minecraft'' is a sandbox game developed by Mojang Studios. The game was created by Markus "Notch" Persson in the Java (programming language), Java programming language. Following several early private testing versions, it was first made pub ...

, supporting capabilities such as spatial reasoning,

real-time strategy Real-time strategy (RTS) is a subgenre of strategy video games that do not progress incrementally in turns, but allow all players to play simultaneously, in "real time". By contrast, in turn-based strategy (TBS) games, players take turns to p ...

, and opponent

anticipation Anticipation is an emotion involving pleasure or anxiety in considering or awaiting an expected event. Anticipatory emotions include fear, anxiety, hope and trust. When the anticipated event fails to occur, it results in disappointment (if posit ...

. AI agents have also been created for video games including Infinite

Mario is a character created by Japanese video game designer Shigeru Miyamoto. He is the title character of the ''Mario'' franchise and the mascot of Japanese video game company Nintendo. Mario has appeared in over 200 video games since his cre ...

which used reinforcement learning, and Frogger II,

Space Invaders is a 1978 shoot 'em up arcade game developed by Tomohiro Nishikado. It was manufactured and sold by Taito in Japan, and licensed to the Midway division of Bally for overseas distribution. ''Space Invaders'' was the first fixed shooter an ...

, and Fast Eddie, which used both reinforcement learning and

mental image A mental image is an experience that, on most occasions, significantly resembles the experience of 'perceiving' some object, event, or scene, but occurs when the relevant object, event, or scene is not actually present to the senses. There are ...

ry. Soar can run natively on

mobile device A mobile device (or handheld computer) is a computer small enough to hold and operate in the hand. Mobile devices typically have a flat LCD or OLED screen, a touchscreen interface, and digital or physical buttons. They may also have a physica ...

s. A mobil
application
for the game Liar’s Dice has been developed for

iOS iOS (formerly iPhone OS) is a mobile operating system created and developed by Apple Inc. exclusively for its hardware. It is the operating system that powers many of the company's mobile devices, including the iPhone; the term also include ...

which runs the Soar architecture directly from the phone as the engine for opponent AIs.

Robotics

Many different robotic applications have been built using Soar since the original Robo-Soar was implemented in 1991 for controlling a Puma robot arm. These have ranged from mobile robot control to humanoid service REEM robots, taskable robotic mules and unmanned underwater vehicles.

Interactive task learning

A current focus of research and development in the Soar community is Interactive Task Learning (ITL), the automatic learning of new tasks, environment features, behavioral constraints, and other specifications through natural instructor interaction. Research in ITL has been applied to tabletop game playing and multi-room navigation.

Scheduling

Early on, Merle-Soar demonstrated how Soar could learn a complex scheduling task modeled after the lead human scheduler in a windshield production plant located near Pittsburgh.

References

{{Reflist , refs= {{cite book, last=Laird, first=John E., date=2012, url=https://mitpress.mit.edu/books/soar-cognitive-architecture, title=The Soar Cognitive Architecture , publisher=

MIT Press The MIT Press is a university press affiliated with the Massachusetts Institute of Technology (MIT) in Cambridge, Massachusetts (United States). It was established in 1962. History The MIT Press traces its origins back to 1926 when MIT publish ...

, isbn= 978-0262122962 {{cite journal, last1=Laird, first1=John, last2=Newell, first2=Allen, date=1983, title= A Universal Weak Method: Summary of results, journal=IJCAI, volume=2, pages=771–772, url=http://dl.acm.org/citation.cfm?id=1623558 {{cite journal, last1=Rosenbloom, first1=Paul, last2=Laird, first2=John, last3=Mcdermott, first3=John, title=R1-Soar: An Experiment in Knowledge-Intensive Programming in a Problem-Solving Architecture, journal=IEEE Transactions on Pattern Analysis and Machine Intelligence, date=27 January 2009, volume=PAMI-7, issue=5, pages=561–569, doi=10.1109/TPAMI.1985.4767703, pmid=21869293, s2cid=16133794 {{cite book , last=Newell , first=Allen , date=December 1990 , title=Unified Theories of Cognition , publisher=Harvard University Press , isbn=978-0674920996 , url-access=registration , url=https://archive.org/details/unifiedtheorieso0000newe {{cite journal, last1=Cohen, first1=Philip, last2=Levesque, first2=Hector, title=Confirmations and joint action, journal=IJCAI, date=1991, volume=2, pages=951–957, url=http://dl.acm.org/citation.cfm?id=1631603 {{cite journal, last1=Rubinoff, first1=Robert, last2=Lehman, first2=Jill, title=Real-time natural language generation in NL-Soar, journal=INLG, volume=Proceedings of the Seventh International Workshop on Natural Language Generation, date=1994, pages=199–206, doi=10.3115/1641417.1641440, s2cid=13885938, url=http://dl.acm.org/citation.cfm?id=1641440, doi-access=free {{cite journal, last1=Nelson, first1=G, last2=Lehman, first2=J, last3=John, first3=B, title=Integrating cognitive capabilities in a real-time task, journal=Proceedings of the 16th Annual Conference of the Cognitive Science Society, date=1994, pages=658–663, url=https://www.bibsonomy.org/bibtex/d8033d7496b2f034268d170b45686fb7 {{cite journal, last1=Tambe, first1=Milind, title=Agent Architectures for Flexible, Practical Teamwork, journal=AAAI, volume=Proceedings of the fourteenth national conference on artificial intelligence and ninth conference on Innovative applications of artificial intelligence, date=1997, pages=22–28, url=http://dl.acm.org/citation.cfm?id=1867410 {{cite journal, last1=van Lent, first1=Michael, last2=Laird, first2=John, title=Developing an artificial intelligence engine, date=1991, url=https://www.researchgate.net/publication/243763189 {{cite book, last1=Laird, first1=John, title=It Knows What You'Re Going to Do: Adding Anticipation to a Quakebot, journal=Agents, date=2001, volume=Proceedings of the Fifth International Conference on Autonomous Agents, pages=385–392, doi=10.1145/375735.376343, isbn=978-1581133264, s2cid=3509100 {{cite journal, last1=Laird, first1=John, last2=Yager, first2=Eric, last3=Hucka, first3=Michael, last4=Tuck, first4=Christopher, title=Robo-Soar: An integration of external interaction, planning, and learning using Soar, journal=Robotics and Autonomous Systems, date=November 1991, volume=8, issue=1–2, pages=113–129, doi=10.1016/0921-8890(91)90017-f, citeseerx=10.1.1.726.7247, hdl=2027.42/29045 {{cite journal, last1=Lieto, first1=Antonio, last2=Perrone, first2=Federico, last3=Pozzato, first3=Gian Luca, last4=Chiodino, first4=Eleonora, date=2019, title= Beyond Subgoaling: A Dynamic Knowledge Generation Framework for Creative Problem Solving in Cognitive Architectures, journal=Cognitive Systems Research, volume=58, pages=305–316, doi=10.1016/j.cogsys.2019.08.005, hdl=2318/1726157, s2cid=201127492, hdl-access=free {{cite journal, last1=Wray, first1=Robert, display-authors=etal, title=Intelligent opponents for virtual reality trainers, journal=I/Itsec, date=December 2002, volume=Proceedings of the Interservice/Industry Training, Simulation and Education Conference, citeseerx=10.1.1.549.2187 {{cite journal, last1=Mohan, first1=Shiwali, last2=Laird, first2=John, title=Learning to Play Mario, journal=Technical Report, date=2009, volume=CCA-TR-2009-03, citeseerx=10.1.1.387.5972 {{cite journal, last1=Wintermute, title=Imagery in Cognitive Architecture: Representation and Control at Multiple Levels of Abstraction, journal=Cognitive Systems Research, date=September 2012, volume=19-20, pages=1–29, doi=10.1016/j.cogsys.2012.02.001, url=http://dl.acm.org/citation.cfm?id=2619015, citeseerx=10.1.1.387.5894, s2cid=15399199 {{cite journal, last1=Turner, first1=Alex, title=Soar-SC: A Platform for AI Research in StarCraft, date=2013, url=https://github.com/bluechill/Soar-SC {{cite journal, date=February 2013, journal=Office of Naval Research, volume=11, title=The Mystery of Artificial Intelligence, url=https://www.onr.navy.mil/Science-Technology/Directorates/office-innovation/~/media/Files/03I/DoI-News-FEB2014-Vol11pdf {{cite journal, date=2014, last1=Laird, first1=John, title=NSF Report: Interactive Task Learning, url=http://web.eecs.umich.edu/~soar/sitemaker/docs/pubs/ITL_Report_NSF_1419590.pdf {{cite journal, last1=Kirk, first1=James, last2=Laird, first2=John, title=Learning General and Efficient Representations of Novel Games Through Interactive Instruction, journal=Advanced Cognitive Systems, date=2016, volume=4, url=http://www.cogsys.org/papers/ACS2016/Papers/Kirk_Laird-ACS-2016.pdf {{cite journal, last1=Mininger, first1=Aaron, last2=Laird, first2=John, title=Interactively Learning Strategies for Handling References to Unseen or Unknown Objects, journal=Advanced Cognitive Systems, date=2016, url=http://www.cogsys.org/papers/ACS2016/Papers/Mininger_Laird-ACS-2016.pdf {{cite journal, date=2001, last1=van Lent, first1=Mike, display-authors=etal, url=http://web.eecs.umich.edu/~soar/sitemaker/workshop/22/vanLentMRE-S22.PDF, title=ICT Mission Rehearsal Exercise {{cite journal, last1=Jones, display-authors=etal, title=Automated Intelligent Pilots for Combat Flight Simulation, journal=AAAI, date=1999, volume=20, issue=1, url=http://www.aaai.org/ojs/index.php/aimagazine/article/view/1438 {{cite journal, last1=Puigbo, first1=Jordi-Ysard, display-authors=etal, title=Controlling a General Purpose Service Robot By Means Of a Cognitive Architecture, journal=AIC, date=2013, volume=45, citeseerx=10.1.1.402.5541 {{cite journal, last1=Talor, first1=Glen, display-authors=etal, title=Multi-Modal Interaction for Robotic Mules, journal=Soar Technology Inc., date=February 2014 {{cite journal, last1=Jones, first1=Steven, display-authors=etal, title=Efficient Computation of Spreading Activation Using Lazy Evaluation, journal=ICCM, date=2016, volume=Proceedings of the 14th International Conference on Cognitive Modeling, pages=182–187, url=http://acs.ist.psu.edu/iccm2016/proceedings/jones2016iccm.pdf ''SoarTech: JSoar''
/ref>

Bibliography

* Laird, 201
The Soar Cognitive Architecture
* Lehman, Laird, and Rosenbloom, 200
A Gentle Introduction to Soar: 2006 update
* Rosenbloom, Laird, and Newell, 199

Information Sciences Institute

External links

Soar Homepage
on

Soar: Frequently Asked Questions ListSoar Tech HomepagePaul Rosenbloom
Agent-based programming languages Cognitive architecture