The hedonic agent: A constructivist approach of abductive capacities
The most important question that autonomous agents have to answer is how to remain viable in various and changing environments despite their bounded cognitive capacities. This question is thus the same as how their semiotic capacity to guess viable solutions emerges, that is abduction. The claim is that no learning can happen without a hedonic principle. That defines the hedonic level.
The hedonic level is presented as a cognitive paradigm: the hedonic agent can auto teach its hedonic and sensorimotor anticipations and also the meaningful and useful distinctions for these anticipations. That defines the possibility of the emergence of a job architecture, in a constructivist way.
A model of emergence of abductive capacities inside an architecture of jobs and inside jobs is proposed. This model takes into account both the limited cognitive capacities of the agent and its necessity to manage continuously its compromise between exploration and exploitation. The claim is that, inside its job architecture, the hedonic agent can use only forward policies because of its bounded cognitive capacities. The theory of bandit processes provides the optimality of such policies based on the index of Gittins and their pertinence for the compromise between exploration and exploitation. A new learning rule of reinforcement, the I-Learning rule, is proposed to evaluate this index.
KeywordsCompletion Time Markov Decision Process Index Policy Sensorimotor System Cognitive Paradigm
Unable to display preview. Download preview PDF.
- Aubin J.P.,1991. Viability Theory, Birkhäuser.Google Scholar
- Baum Eric B., David Haussler, 1989, What Size Net Gives Valid Generalization? Neural Computation 1, 151–160 (1989).Google Scholar
- Bourgine P., F. Varela 1992. Towards a practice of autonomous system. in Towards a practice of autonomous system, F.Varela & P.Bourgine (ed). MIT Press/Bradford Books.pp 3–10.Google Scholar
- Bourgine P., 1993, Viability and pleasure satisfaction principle of autonomous systems, in Imagina-93 proc.Google Scholar
- Brooks R., 1991. Intelligence without reason. IICAI-91, Sydney.Google Scholar
- Gittins J.C., 1989, Multi-armed Bandit. Allocation Indices, John Wiley & SonsGoogle Scholar
- Edelman, G, 1992, Bright Air, Brillant Fire: On the Matter of Mind, Basic Books.Google Scholar
- Holland, J.H., 1975. Adaptation in natural and artificial systems. Ann Arbor: the university of Michigan Press.Google Scholar
- Kohonen T., 1984. Self-Organization and Associative Memory. Springer Verlag.Google Scholar
- Langton C., 1989. (ed) Artificial Life I, Addison Wesley.Google Scholar
- Langten C., 1992,Life at the edge of chaos, in Artificial Life II, Addison-Wesley, p.41–92, 1992.Google Scholar
- Meyer Jean-Arcady, Wilson Stewart W., 1991, From animals to animats, M.I.T./Bradford Book, Cambridge,MA.Google Scholar
- Nicolis G., I.Prigogine, Exploring Complexity: An Introduction. R.Piper GmbH & Co. KG Verlag, 1989.Google Scholar
- Peirce Charles S., Textes fondamentaux de sémiotique, Méridiens Klincksiek, Paris, 1987.Google Scholar
- Petitot J., 1990, Physique du sens, editions du CNRS.Google Scholar
- Rosh E., 1978, Principles of Categorization, in Cognition and Categorization, ed. E.Rosh and B.B.Lloyd, Lawrence Erlbaum, Hillsdalle, N.J., 27–48.Google Scholar
- Rumelhart D.E. and J.Mc Clelland, 1986, Parallel Distributed Processing, MIT Press/ Bradford Books.Google Scholar
- Simon H.A. (1976) From subtantive to procedural rationality. Method and Appraisal in Economics, Latsis S.J.(ed.), p. 129–148. Cambridge University Press, Cambridge.Google Scholar
- Sutton, R.S., 1988, Learning to predict by the methods of temporal difference. Machine Learning., 3, 9–44.Google Scholar
- Valiant L.G., 1984, A theory of the learnable, Communications of the ACM V27, n∘11 pp. 1184–1142.Google Scholar
- Vapnik V.N. et Y. Chervonenkis, 1981. On the uniform convergence of relative frequencies of events to their probabilities. In Theory of probability and its applications, XXVI, pp 532–553.Google Scholar
- Varela F., 1979. Principles of Biological Autonomy, North Holland, Amsterdam.Google Scholar
- Varela F., 1986. Trends in Cognitive Science and Technology. in: J.L. Roos (ed.), Economics and Artificial Intelligence. Pergamon Press, Oxford, pp. 1–8.Google Scholar
- Varela F., E. Thompson & E. Rosch, 1991, The Embodied Mind. MIT Press.Google Scholar
- Varela F., P.Bourgine, 1992, Towards a practice of autonomous system, MIT Press/Bradford Books.Google Scholar
- Walliser B., 1993, A spectrum of cognitive processes in game theory, in Second European Congress on System Science, Prague, oct 93.Google Scholar
- Watkins C., 1989, Learning with Delayed Reward, PhD, Cambridge University Psychology Department.Google Scholar