A brain model-based alternative to reinforcement learning is presented that integrates artificial neural networks and knowledge-based systems into one unit or agent for goal-oriented problem solving. The agent may possess inherited and learned artificial neural networks and knowledge-based subsystems. The agent has and develops ANN cues to the environment for dimensionality reduction (data compression) to ease the problem of combinatorial explosion. Here, a dynamical concept model is put forward that builds cue models of the phenomena in the world, designs dynamical action sets (concepts), and makes them compete in a spreading-activation neural stage to reach decision. The agent works under closed-loop control. Here we examine a simple robotlike object in a two-dimensional conditionally probabilistic space.
Agranat, A.J., Neugebauer, C.F., & Yariv, Y. (1990). The CCD neural processor: A neural network integrated circuit with 65536 programmable synapses. IEEE Transactions on Circuits and Systems, 37, 1073-1075.
2.
Agranat, A.J., & Yariv, Y. (1987). Semiparallel microelectronic implementation of neural network models using CCD technology. Electronics Letters , 23, 580-582.
3.
Anderson, C.W. (1987). Strategy learning with multilayer connectionist representation. In Proceedings of the Fourth International Workshop on Machine Learning, Ann Arbor, MI.
4.
Barto, A., Bradtke, S., & Singh, S. (1991). Real-time learning and control using asynchronous dynamic programming (Tech. Rep. No. 91-57). Boston: Computer Science Department, University of Massachusetts.
5.
Bundy, A. (Ed.). (1990). Catalogue of artificial intelligence techniques. (3rd ed.). Heidelberg : Springer-Verlag.
Chapman, D., & Kaelbling, L.P. (1991). Input generalization in delayed reinforcement learning: An algorithm and performance comparisons. In Proceedings of the International Joint Conference on Artificial Intelligence, Sydney, Australia.
8.
Cloak, E.T., Jr. (1975). Is cultural ecology possible? Human Ecology, 3, 161-182.
9.
Collins, A., & Loftus, E. (1975). A spreading activation theory of semantic processing . Psychological Review, 82, 407-428.
10.
Csànyi, V. (1982). General theory of evolution. Budapest: Akadémiai Könyvkiadó.
11.
Földiák, P. (1991). Learning invariance from transformation sequences . Neural Computation, 3(2), 194-200.
12.
Fomin, T., & Lórincz, A. (1993). On the potential of Hebbian and anti-Hebbian learning . Manuscript submitted for publication.
13.
Fukushima, K. (1992). Character recognition with neural networks. Neural Computing, 4, 221-233.
14.
Grossberg, S.A. (1968). Some nonlinear networks capable of learning a spatial pattern of arbitrary complexity. Proceedings of the National Academy of Sciences, 59, 368-372.
15.
Hebb, D.O. (1949). The organization of behavior. New York: Wiley
16.
Hertz, J., Krogh, A., & Palmer, R.G. (1991). Introduction to the theory of neural computation . Redwood City: Addison-Wesley .
17.
Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural Networks, 2, 359-366.
18.
Huberman, B.A., & Hogg, T. (1987). Phase transition in artificial intelligence systems . Artificial Intelligence, 33, 155-171.
19.
Judd, J.S. (1990). Neural network design and the complexity of learning . Cambridge, MA: MIT Press.
20.
Korf, R.E. (1990). Real time heuristic search. Artificial Intelligence, 42, 189-211.
21.
Lin, L.-J. (1990). Self-improving reactive agents: Case studies of reinforcement learning framework. (Tech. Rep. No. CMU-CS-90-109). Pittsburgh: Carnegie-Mellon University .
22.
Maes, P. (1992). Learning behavior networks from experience. In F. J. Varela & P. Bourgine (Eds.), Toward a practice of autonomous systems: Proceedings of the First European Conference on Artificial Life. Cambridge, MA: MIT Press.
23.
Olshausen, B., Anderson, C., & Van Essen, D. (1993). A neural model of visual attention and invariant pattern recognition. Manuscript submitted for publication.
24.
Peng, Y., & Reggia, J.A. (1989). A connectionist model for diagnostic problem solving . IEEE Transactions on Systems, Man and Cybernetics, 19, 285-298.
25.
Sutton, R.S. (1988). Learning to predict by the method of temporal differences. Machine Learning, 3, 9-44.
26.
Szepesvàri, C., Balàzs, L., & Lôrincz, A. (in press). Topology learning solved by extended objects: A neural network model. Neural Computation.
27.
Thagard, P. (1989). Explanatory coherence. Behavioral and Brain Sciences, 12, 435-467.
28.
Varela, F. J., & Bourgine, P. (Eds.) (1992). Toward a practice of autonomous systems: Proceedings of the First European Conference on Artificial Life. Cambridge, MA: MIT Press.
Widrow, B., Gupta, N.K., & Maitra, S. (1973). Punish/reward: Learning with critic in adaptive threshold systems. IEEE Transactions on Systems, Man and Cybernetics SMC-3, 455-465.
