Abstract
In this paper we discuss how to design a simple motivated learning agent with symbolic I/O using a simulation environment within the NeoAxis game engine. The purpose of this work is to explore autonomous development of motivations and memory of agents in a virtual environment. The approach we took should speed up the development process, bypassing the need to create a physical embodied agent as well as reducing the learning effort. By rendering low-level motor actions such as grasping or walking into symbolic commands we remove the need to learn elementary motions. Instead, we use several basic primitive motor procedures, which can form more complex procedures. Furthermore, by simulating the agent’s environment, we both improve and simplify the learning process. There are a few adaptive learning variables associated with both the agent and its environment, and learning takes less time, than it would in a more complex real world environment.
Chapter PDF
Similar content being viewed by others
References
Hirukawa, H., et al.: Humanoid robotics platforms developed in HRP. Robotics and Autonomous Systems 48(4), 165–175 (2004)
Bakker, B., Schmidhuber, J.: Hierarchical Reinforcement Learning Based on Subgoal Discovery and Subpolicy Specialization. In: Groen, F., Amato, N., Bonarini, A., Yoshida, E., Köse, B. (eds.) Proceedings of the 8th Conference on Intelligent Autonomous Systems, IAS-8, Amsterdam, The Netherlands, pp. 438–445 (2004)
Oudeyer, P.-Y., et al.: Intrinsically Motivated Exploration for Developmental and Active Sensorimotor Learning. In: Sigaud, O., Peters, J. (eds.) From Motor Learning to Interaction Learning in Robots. SCI, vol. 264, pp. 107–146. Springer, Heidelberg (2010)
Ro, S., et al.: Curiosity-driven acquisition of sensorimotor concepts using memory-based active learning. In: IEEE Intl. Conf. on Robotics and Biometrics, pp. 665–670 (2009)
Singh, S., Barto, A.G., Chentanez, N.: Intrinsically motivated learning of hierarchical collections of skills. In: Proc. 3rd Int. Conf. Development Learn., San Diego, CA, pp. 112–119 (2004)
Laird, J.E.: Extending the Soar cognitive architecture. In: Artificial General Intelligence 2008, pp. 224–235. IOS Press, Memphis (2008)
Anderson, J.R., et al.: An integrated theory of the mind. Psych. Review 111(4), 1036–1060 (2004)
Langley, P., Choi, D.: A unified cognitive architecture for physical robots. In: 21st Nat. Conf. Artificial Intelligence, pp. 1469–1474. AAAI Press, Boston (2006)
Baars, B.J., Franklin, S.: Consciousness is computational: the LIDA model of global workspace theory. Int. J. Machine Consciousness 1(1), 23–32 (2009)
Cassimatis, N., Nicholas, L.: Polyscheme: A Cognitive Architecture for Integrating Multiple Represetnation and Inference Schemes, MIT Ph.D. Diss. (2002)
Sun, R.: The importance of cognitive architectures: an analysis based on CLARION. J. Experimental and Theor. Artif. Intell. 19(2), 159–193 (2007)
Brooks, R.A.: Intelligence without reason. In: Proc. 12th Int. Conf. on Artificial Intelligence, Sydney, Australia, pp. 569–595 (1991)
Pfeifer, R., Bongard, J.C.: How the Body Shapes the Way We Think: A New View of Intelligence. The MIT Press, Bradford Books (2007)
Starzyk, J.A.: Motivation in Embodied Intelligence. In: Frontiers in Robotics, Automation and Control, pp. 83–110. I-Tech Education and Publishing, Austria (2008)
Clark, A.: Reasons, Robots and the Extended Mind. J. Mind and Language 16(2), 121–145 (2001)
Kanda, T., et al.: Development and evaluation of interactive humanoid robots. Proceedings of IEEE 92(11), 1839–1850 (2004)
Weng, J., et al.: Autonomous mental development by robots and animals. Science 291(5504), 599–600 (2001)
Starzyk, J.A.: Motivated Learning for Computational Intelligence. In: Igelnik, B. (ed.) Computational Modeling and Simulation of Intellect: Current State and Future Perspectives, ch.11, pp. 265–292. IGI Publishing (2011)
Starzyk, J.A.: Mental Saccades in Control of Cognitive Process. In: Int. Joint Conf. on Neural Networks, San Jose, CA, July 31-August 5, pp. 495–502 (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 IFIP International Federation for Information Processing
About this paper
Cite this paper
Starzyk, J.A., Graham, J., Puzio, L. (2013). Simulation of a Motivated Learning Agent. In: Papadopoulos, H., Andreou, A.S., Iliadis, L., Maglogiannis, I. (eds) Artificial Intelligence Applications and Innovations. AIAI 2013. IFIP Advances in Information and Communication Technology, vol 412. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41142-7_21
Download citation
DOI: https://doi.org/10.1007/978-3-642-41142-7_21
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41141-0
Online ISBN: 978-3-642-41142-7
eBook Packages: Computer ScienceComputer Science (R0)