Motivational Engine with Sub-goal Identification in Neuroevolution Based Cognitive Robotics

详细信息    查看全文

• 关键词：Neuroevolution ; Cognitive systems ; Motivation ; Autonomous robots
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9648
• 期：1
• 页码：659-670
• 全文大小：811 KB
• 参考文献：1.Ryan, R.M., Deci, E.L.: Intrinsic and extrinsic motivations: classic definitions and new directions. Contemp. Educ. Psychol. 25, 54–67 (2000)CrossRef
  2.Scott, P.D., Markovitch, S.: Learning novel domains through curiosity and conjecture. In: Proceedings IJCAI 1989, pp. 669–674 (1989)
  3.Shmidhuber, J.: Adaptive confidence and adaptive curiosity. Technical Report. Institut fur Informatik, Technische Universität Munchen (1991)
  4.Lenat, D.B.: AM: an artificial intelligence approach to discovery in mathematics as heuristic search, Doctoral Dissertation No. STAN-CS-76-570, Department of Computer Science, Stanford University (1976)
  5.Sutton, R.S.: Reinforcement learning architectures for animals. In: From Animals to Animats: Proceedings of the First International Conference on Simulation of Adaptive Behavior, pp. 288–296 (1991)
  6.Oudeyer, P.Y., Kaplan, F.: What is intrinsic motivation? a typology of computational approaches. Front. Neurorobot. 1(A.6), 1–14 (2007)
  7.McGovern, A., Barto, A.: Automatic discovery of subgoals in reinforcement learning using diverse density. Technical report of the faculty publication series, Computer Science Department, University of Massachusetts, Amherst (2001)
  8.Menache, I., Mannor, S., Shimkin, N.: Q-cut - dynamic discovery of sub-goals in reinforcement learning. In: Elomaa, T., Mannila, H., Toivonen, H. (eds.) ECML 2002. LNCS (LNAI), vol. 2430, pp. 295–306. Springer, Heidelberg (2002)CrossRef
  9.Simsek, O., Barto, A.: Betweenness centrality as a basis for forming skills. Technical report, Department of Computer Science, University of Massachusetts (2007)
  10.Mannor, S., Menache, I., Hoze, A., Klein, U.: Dynamic abstraction in reinforcement learning via clustering. In: Proceedings of the Twenty-First International Conference on Machine Learning, pp. 560–567. ACM (2004)
  11.Konidaris, G., Barto, A.: Sensorimotor abstraction selection for efficient, autonomous robot skill acquisition. In: 7th IEEE International Conference on Development and Learning, ICDL 2008, pp. 151–156, (2008)
  12.Salge, C., Glackin, C., Polani, D.: Approximation of empowerment in the continuous domain. Adv. Complex Syst. 16(1–2), 1250079 (2013)MathSciNet CrossRef
  13.Bellas, F., Duro, R.J., Faina, A., Souto, D.: Multilevel Darwinist Brain (MDB): artificial evolution in a cognitive architecture for real robots. IEEE Trans. Auton. Ment. Dev. 2(4), 340–354 (2010)CrossRef
  
• 作者单位：Rodrigo Salgado (17)
  Abraham Prieto (17)
  Pilar Caamaño (17)
  Francisco Bellas (17)
  Richard J. Duro (17)
  
  17. Integrated Group for Engineering Research, Universidade da Coruña, Ferrol, Spain
  
• 丛书名：Hybrid Artificial Intelligent Systems
• ISBN：978-3-319-32034-2
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

A first approach towards a new motivational system for an autonomous robot that can learn chains of sub-goals leading to a final reward is proposed in this paper. The motivational system provides the motivation that guides the robot operation according to its knowledge of its sensorial space so that rewards are maximized during its lifetime. In order to do this, a motivational engine progressively and interactively creates an internal model of expected future reward (value function) for areas of the robot’s state space, through a neuroevolutionary process, over samples obtained in the sensorial (state space) traces followed by the robot whenever it obtained a reward. To improve this modelling process, a strategy is proposed to decompose the global value function leading to the reward or goal into several more local ones, thus discovering sub-goals that simplify the whole learning process and that can be reused in the future. The motivational engine is tested in a simulated experiment with very promising results.