Strategy Learning with Multilayer Connectionist Representations 1

  title={Strategy Learning with Multilayer Connectionist Representations 1},
  author={Charles W. Anderson},
Results are presented that demonstrate the learning and ne-tuning of search strategies using connectionist mechanisms. Previous studies of strategy learning within the symbolic, production-rule formalism have not addressed ne-tuning behavior. Here a two-layer connectionist system is presented that develops its search from a weak to a task-speci c strategy and ne-tunes its performance. The system is applied to a simulated, realtime, balance-control task. We compare the performance of one-layer… CONTINUE READING
Highly Influential
This paper has highly influenced 23 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
110 Citations
19 References
Similar Papers


Publications referenced by this paper.
Showing 1-10 of 19 references

Temporal aspects of credit assignment in reinforcement learning

  • R. S. Sutton
  • Doctoral Dissertation, Department of Computer and…
  • 1984
Highly Influential
3 Excerpts

Doing, understanding, and production systems

  • Y. Anzai
  • Production system models of learning and…
  • 1987
2 Excerpts

Learning to predict by the methods of temporal di erences. (Technical Report TR87-509.1)

  • R. S. Sutton
  • 1987
1 Excerpt

Production system models of learning and development

  • D. Klahr, P. Langley, R. Neches
  • 1987

Learning internal representations by error propagation

  • D. E. Rumelhart, G. E. Hinton, R. Williams
  • 1986
1 Excerpt

Similar Papers

Loading similar papers…