Cognitive Architectures for Physical Agents

Icarus is a computational theory of the cognitive architecture that incorporates ideas from multiple traditions, including work on production systems, hierarchical task networks, and logic programming. The framework relies on five assumptions that distinguish it from alternative candidates:

  • Cognition is grounded in perception and action;
  • Categories and skills are distinct types of cognitive structure;
  • Short-term elements are instances of long-term structures;
  • Long-term knowledge is organized in a hierarchical manner; and
  • Inference has primacy over execution, which has primacy over problem solving.
  • Our papers explain these assumptions and particular abilities in more detail. We have used Icarus to develop a number of synthetic characters for simulated environments, as well as for traditional tasks from the AI and cognitive science literature. Current research includes incorporating mechanisms for forward-chaining problem solving, counterfactual reasoning, model-based learning from delayed reward, generating episodic traces, and learning from other agents' behaviors.

    This research has been funded by DARPA IPTO, the Office of Naval Research, and the National Science Foundation. Support for earlier work came from the Air Force Office of Scientific Research, NASA Ames Research Center, and DaimlerChrysler Research and Technology.


    Alternative / Succsessor Architectures

    Langley, P., & Katz, E. P. (in press). Spatial representation and reasoning in an architecture for embodied agents. Spatial Cognition and Computation: An Interdisciplinary Journal.

    Langley, P., & Katz, E. P. (2022). Motion planning and continuous control in a unified cognitive architecture. Proceedings of the Tenth Annual Conference on Advances in Cognitive Systems. Arlington, VA.

    Langley, P., & Katz, E. P. (2022). Extending an embodied cognitive architecture with spatial representation and reasoning. Proceedings of the Third International Workshop on Human-Like Computing. Windsor Great Park, UK.

    Langley, P. (2022). Representing and processing emotions in a cognitive architecture. Proceedings of the Third International Workshop on Human-Like Computing. Windsor Great Park, UK.

    Langley, P., Choi, D., Barley, M., Meadows, B., & Katz, E. P. (2017). Generating, executing, and monitoring plans with goal-based utilities in continuous domains. Proceedings of the Fifth Annual Conference on Cognitive Systems. Troy, NY.

    Langley, P., Barley, M., Meadows, B., Choi, D., & Katz, E. P. (2016). Goals, utilities, and mental simulation in continuous planning. Proceedings of the Fourth Annual Conference on Cognitive Systems. Evanston, IL.

    Langley, P. (2016). An architectural account of variation in problem solving and execution. Proceedings of the Thirty-Eighth Annual Meeting of the Cognitive Science Society. Philadelphia, PA.

    Langley, P., Pearce, C., Bai, Y., Barley, M., & Worsfold, C. (2016). Variations on a theory of problem solving. Proceedings of the Fourth Annual Conference on Cognitive Systems. Evanston, IL.

    Bai, Y., Pearce, C., Langley, P., Barley, M., & Worsfold, C. (2015). An architecture for flexibly interleaving planning and execution. Poster Collection: The Third Annual Conference on Advances in Cognitive Systems. Atlanta, GA.

    Langley, P., Emery, M., Barley, M., & MacLellan, C. (2013). An architecture for flexible problem solving. Poster Collection: The Second Annual Conference on Advances in Cognitive Systems (pp. 93-110). Baltimore, MD.


    Recent Versions of ICARUS

    Choi, D., & Langley, P. (2018). Evolution of the ICARUS cognitive architecture. Cognitive Systems Research, 48, 25-38.

    Choi, D., Langley, P., & To, S. T. (in press). Creating and using tools in a hybrid cognitive architecture. Proceedings of the AAAI Spring Symposium on Integrating Representation, Reasoning, Learning, and Execution for Goal Directed Autonomy. Stanford, CA: AAAI Press.

    Langley, P., & Trivedi, N. (2013). Elaborations on a theory of human problem solving. Poster Collection: The Second Annual Conference on Advances in Cognitive Systems (pp. 111-122). Baltimore, MD.

    Li, N., Stracuzzi, D. J., & Langley, P. (2012). Improving acquisition of teleoreactive logic programs through representation extension. Advances in Cognitive Systems, 1, 109-126.

    Trivedi, N., Langley, P., Schermerhorn, P., & Scheutz, M. (2011). Communicating, interpreting, and executing high-level instructions for human-robot interaction. Proceedings of the AAAI Fall Symposium on Advances in Cognitive Systems. Arlington, VA: AAAI Press.

    Bridewell, W., & Langley, P. (2011). A computational account of everyday abductive inference. Proceedings of the Thirty-Third Annual Meeting of the Cognitive Science Society. Boston.

    Iba, W. F., & Langley, P. (2011). Exploring moral reasoning in a cognitive architecture. Proceedings of the Thirty-Third Annual Meeting of the Cognitive Science Society. Boston.

    Langley, P., Trivedi, N., & Banister, M. (2010). A command language for taskable virtual agents. Proceedings of the Sixth Conference Artificial Intelligence and Interactive Digital Entertainment. Stanford, CA: AAAI Press.

    Danielescu, A., Stracuzzi, D. J., Li, N., & Langley, P. (2010). Learning from errors by counterfactual reasoning in a unified cognitive architecture. Proceedings of the Thirty-Second Annual Meeting of the Cognitive Science Society. Portland.

    Li, N., Stracuzzi, D. J., Langley, P., & Nejati, N. (2009). Learning hierarchical skills from problem solutions using means-ends analysis. Proceedings of the Thirty-First Annual Meeting of the Cognitive Science Society. Amsterdam.

    Stracuzzi, D. J., Li, N., Cleveland, G., & Langley, P. (2009). Representing and reasoning over time in a unified cognitive architecture. Proceedings of the Thirty-First Annual Meeting of the Cognitive Science Society (pp. 2986-2991). Amsterdam.

    Konik, T., O'Rorke, P., Shapiro, D., Choi, D., Nejati, N., & Langley, P. (2009). Skill transfer through goal-driven representation mapping. Cognitive Systems Research, 10, 270-285.

    Langley, P., Choi, D., & Rogers, S. (2009). Acquisition of hierarchical reactive skills in a unified cognitive architecture. Cognitive Systems Research, 10, 316-332.

    Li, N., Stracuzzi, D., Cleveland, G., Langley, P., Konik, T., Shapiro, D., Ali, K., Molineaux, M., & Aha, D. (2009). Learning hierarchical skills for game agents from video of human behavior. Proceedings of the IJCAI-09 Workshop on Learning Structural Knowledge from Observations. Pasadena, CA.

    Li, N., Stracuzzi, D., & Langley, P. (2008). Learning conceptual predicates for teleoreactive logic programs. Proceedings of the Eighteenth International Conference on Inductive Logic Programming. Prague: Springer.

    Langley, P. (2007). Varieties of problem solving in a unified cognitive architecture. Proceedings of the Twenty-Ninth Annual Meeting of the Cognitive Science Society. Nashville, TN.

    Choi, D., Konik, T., Nejati, N., Park, C., & Langley, P. (2007). Structural transfer of cognitive skills. Proceedings of the Eighth International Conference on Cognitive Modeling. Ann Arbor, MI.

    Choi, D., Konik, T., Nejati, N., Park, C., & Langley, P. (2007). A believable agent for first-person shooter games. Proceedings of the Third Annual Artificial Intelligence and Interactive Digital Entertainment Conference (pp. 71-73). Stanford, CA: AAAI Press.

    Langley, P., & Choi, D. (2006). A unified cognitive architecture for physical agents. Proceedings of the Twenty-First National Conference on Artificial Intelligence. Boston: AAAI Press.

    Nejati, N., Langley, P., & Konik, T. (2006). Learning hierarchical task networks by observation. Proceedings of the Twenty-Third International Conference on Machine Learning (pp. 665-672). Pittsburgh, PA.

    Asgharbeygi, N., Stracuzzi, D., & Langley, P. (2006). Relational temporal difference learning. Proceedings of the Twenty-Third International Conference on Machine Learning (pp. 49-56). Pittsburgh, PA.

    Langley, P. (2006). Cognitive architectures and general intelligent systems. AI Magazine, 27, 33-44.

    Langley, P., & Choi, D. (2006). Learning recursive control programs from problem solving. Journal of Machine Learning Research, 7, 493-518

    Langley, P. (2005). An adaptive architecture for physical agents. Proceedings of the 2005 IEEE/WIC/ACM International Conference on Intelligent Agent Technology (pp. 18-25). Compiegne, France: IEEE Computer Society Press.

    Choi, D., & Langley, P. (2005). Learning teleoreactive logic programs from problem solving. Proceedings of the Fifteenth International Conference on Inductive Logic Programming (pp. 51-68). Bonn, Germany: Springer.

    Asgharbeygi, N., Nejati, N., Langley, P., & Arai, S. (2005). Guiding inference through relational reinforcement learning. Proceedings of the Fifteenth International Conference on Inductive Logic Programming (pp. 20-37). Bonn, Germany: Springer.

    Langley, P., & Rogers, S. (2005). An extended theory of human problem solving. Proceedings of the Twenty-Seventh Annual Meeting of the Cognitive Science Society. Stresa, Italy.

    Langley, P., Choi, D., & Rogers, S. (2005). Interleaving learning, problem solving, and execution in the Icarus architecture (Technical Report). Computational Learning Laboratory, CSLI, Stanford University, CA.

    Langley, P., & Rogers, S. (2004). Cumulative learning of hierarchical skills. Proceedings of the Third International Conference on Development and Learning. San Diego, CA: IEEE Press.

    Langley, P. (2004). Cognitive architectures and the construction of intelligent agents. Proceedings of the AAAI-2004 Workshop on Intelligent Agent Architectures (pp. 82). Stanford, CA.

    Langley, P., Arai, S., & Shapiro, D. (2004). Model-based learning with hierarchical relational skills. Proceedings of the ICML-2004 Workshop on Relational Reinforcement Learning. Banff, Alberta.

    Langley, P., Cummings, K., & Shapiro, D. (2004). Hierarchical skills and cognitive architectures. Proceedings of the Twenty-Sixth Annual Conference of the Cognitive Science Society (pp. 779-784). Chicago, IL.

    Choi, D., Kaufman, M., Langley, P., Nejati, N., & Shapiro, D. (2004). An architecture for persistent reactive behavior. Proceedings of the Third International Joint Conference on Autonomous Agents and Multi Agent Systems (pp. 988-995). New York: ACM Press.

    Langley, P., Choi, D., & Shapiro, D. (2004). A cognitive architecture for physical agents (Technical Report). Institute for the Study of Learning and Expertise, Palo Alto, CA.


    Intermediate Versions of ICARUS

    Ichise, R., Shapiro, D., & Langley, P. (in press). Structured program induction from behavioral traces. IEICE Transactions on Information and Systems (in Japanese).

    Langley, P., Shapiro, D., Aycinena, M., & Siliski, M. (2003). A value-driven architecture for intelligent behavior. Proceedings of the IJCAI-2003 Workshop on Cognitive Modeling of Agents and Multi-Agent Interactions (pp. 10-18). Acapulco, Mexico.

    Ichise, R., Shapiro, D. G., & Langley, P. (2002). Learning hierarchical skills from observation (pp. 247-258). Proceedings of the Fifth International Conference on Discovery Science.

    Shapiro, D., & Langley, P. (2002). Separating skills from preference: Using learning to program by reward. Proceedings of the Nineteenth International Conference on Machine Learning (pp. 570-577). Sydney: Morgan Kaufmann.

    Shapiro, D., Langley, P., & Shachter, R. (2001). Using background knowledge to speed reinforcement learning in physical agents. Proceedings of the Fifth International Conference on Autonomous Agents (pp. 254-261). Montreal: ACM Press.

    Shapiro, D., & Langley, P. (1999). Controlling physical agents through reactive logic programming. Proceedings of the Third International Conference on Autonomous Agents (pp. 386-387). Seattle: ACM Press.

    Langley, P. (1997). Learning to sense selectively in physical domains. Proceedings of the First International Conference on Autonomous Agents (pp. 217-226). Marina del Rey, CA: ACM Press.

    Langley, P., Iba, W., & Shrager, J. (1994). Reactive and automatic behavior in plan execution. Proceedings of the Second International Conference on AI Planning Systems (pp. 299-304). Chicago: AAAI Press.


    Early Designs for ICARUS

    Langley, P., McKusick, K. B., Allen, J. A., Iba, W. F., & Thompson, K. (1991). A design for the Icarus architecture. SIGART Bulletin, 2, 104-109.

    Langley, P., Thompson, K., Iba, W. F., Gennari, J., & Allen, J. A. (1989). An integrated cognitive architecture for autonomous agents (Technical Report 89-28). Irvine: University of California, Department of Information & Computer Science.

    Iba, W., & Langley, P. (1987). A computational theory of motor learning. Computational Intelligence, 3, 338-350.

    Langley, P., Nicholas, D., Klahr, D., & Hood, G. (1981). A simulated world for modeling learning and development. Proceedings of the Third Conference of the Cognitive Science Society (pp. 274-276). Berkeley, CA.


    Analyses of Cognitive Architectures

    Langley, P. (2017). Progress and challenges in research on cognitive architectures. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (pp. 4870-4876). San Francisco: AAAI Press.

    Langley, P., Laird, J. E., & Rogers, S. (2009). Cognitive architectures: Research issues and challenges. Cognitive Systems Research, 10, 141-160.

    Choi, D., Morgan, M., Park, C., & Langley, P. (2007). A testbed for evaluation of architectures for physical agents. Proceedings of the AAAI-2007 Workshop on Evaluating Architectures for Intelligence. Vancouver, BC: AAAI Press

    For more information, send electronic mail to patrick.w.langley@gmail.com


    © 1997 Institute for the Study of Learning and Expertise. All rights reserved.