Abstract
This article describes the development of reinforcement learning within the Sigma graphical cognitive architecture. Reinforcement learning has been deconstructed in terms of the interactions among more basic mechanisms and knowledge in Sigma, making it a derived capability rather than a de novo mechanism. Basic reinforcement learning – both model-based and model-free – are demonstrated, along with the intertwining of model learning.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. A Bradford Book, MIT Press, Cambridge (1998)
Hutter, M.: Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability. Springer, Berlin (2005)
Sun, R., Slusarz, P., Terry, C.: The interaction of the explicit and the implicit in skill learning: A dual-process approach. Psychological Review 112, 159–192 (2005)
Nason, S., Laird, J.E.: Soar-RL: Integrating reinforcement learning with Soar. Cognitive Systems Research 6, 51–59 (2005)
Rosenbloom, P.S.: Graphical models for integrated intelligent robot architectures. In: AAAI Spring Symposium on Designing Intelligent Robots (2012)
Kschischang, F.R., Frey, B.J., Loeliger, H.: Factor Graphs and the Sum-Product Algorithm. IEEE Transactions on Information Theory 47, 498–519 (2001)
Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Techniques. MIT Press, Cambridge (2009)
Rosenbloom, P.S.: Bridging dichotomies in cognitive architectures for virtual humans. In: AAAI Fall Symposium on Advances in Cognitive Systems (2011)
Newell, A.: Unified Theories of Cognition. Harvard University Press, Cambridge (1990)
Rummery, G.A., Niranjan, M.: On-line Q-learning using connectionist systems (1994)
Watkins, C.J.C.H.: Learning from Delayed Rewards. PhD thesis, Cambridge University (1989)
Rosenbloom, P.S.: Mental imagery in a graphical cognitive architecture. In: Second International Conference on Biologically Inspired Cognitive Architectures (2011)
Rosenbloom, P.S.: Extending Mental Imagery in Sigma. In: Bach, J., Goertzel, B., Iklé, M. (eds.) AGI 2012. LNCS (LNAI), vol. 7716, pp. 272–281. Springer, Heidelberg (2012)
Rosenbloom, P.S.: Combining Procedural and Declarative Knowledge in a Graphical Architecture. In: 10th International Conference on Cognitive Modeling (2010)
Russell, S., Binder, J., Koller, D., Kanazawa, K.: Local learning in probabilistic networks with hidden variables. In: 14th International Joint Conference on AI (1995)
Munos, R., More, A.: Variable resolution discretization in optimal control. Machine Learning 49, 291–323 (2002)
Rosenbloom, P.S.: From Memory to Problem Solving: Mechanism Reuse in a Graphical Cognitive Architecture. In: Schmidhuber, J., Thórisson, K.R., Looks, M. (eds.) AGI 2011. LNCS (LNAI), vol. 6830, pp. 143–152. Springer, Heidelberg (2011)
Bloch, M.K., Laird, J.E.: Heuristic value function revision. In: The 32nd Soar Workshop
Chen, J., Demski, A., Han, T., Morency, L.-P., Pynadath, P., Rafidi, N., Rosenbloom, P.S.: Fusing symbolic and decision-theoretic problem solving + perception in a graphical cognitive architecture. In: Second International Conference on Biologically Inspired Cognitive Architectures (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rosenbloom, P.S. (2012). Deconstructing Reinforcement Learning in Sigma. In: Bach, J., Goertzel, B., Iklé, M. (eds) Artificial General Intelligence. AGI 2012. Lecture Notes in Computer Science(), vol 7716. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35506-6_27
Download citation
DOI: https://doi.org/10.1007/978-3-642-35506-6_27
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35505-9
Online ISBN: 978-3-642-35506-6
eBook Packages: Computer ScienceComputer Science (R0)