Concepts and facilities of a neural reinforcement learning control architecture for technical process control

Neural Computing and Applications

Volumn 8, Issue 4, 1999, Pages 323-338

  Riedmiller, M ^a  

^a UNIVERSITY OF KARLSRUHE   (Germany)

Author keywords

Intelligent control; Neural control; Reinforcement learning; Technical process control

Indexed keywords

EID: 0033233953     PISSN: 09410643     EISSN: None     Source Type: Journal    
DOI: 10.1007/s005210050038     Document Type: Article

References (16)

1. Riedmiller M. Aspects of learning neural control. Proc IEEE International Conference on Systems, Man and Cybernetics, San Antonio, TX, October 1994
2. Narendra KS, Mukhopadhyay S. Intelligent control using neural networks. IEEE Control Systems Magazine 1992; 12(5): 11-18
3. Barto AG, Sutton RS, Watkins CJCH. Learning and sequential decision making. Technical Report COINS TR 89-95, Department of Computer and Information Science, University of Massachusetts, Amherst, September 1989
4. Barto AG, Bradtke SJ, Singh SP. Learning to act using real-time dynamic programming. Artificial Intelligence 1995; (72): 81-138
5. Barto AG, Crites RH. Improving elevator performance using reinforcement learning. In: ME Hasselmo, DS Touretzky, MC Mozer, editors, Advances in Neural Information Processing Systems 8, MIT Press, 1996
6. Dietterich T, Zhang W. A reinforcement-learning approach to job-shop scheduling. Proc 14th International Joint Conference on Artificial Intelligence, 1995
7. Bertsekas DP, Tsitsiklis JN. Neuro Dynamic Programming, Athena Scientific, Belmont, MA, 1996
8. Riedmiller M. Application of sequential reinforcement learning to control dynamic systems. IEEE International Conference on Neural Networks (ICNN '96), Washington, DC, 1996
9. Riedmiller M. Reinforcement learning without an explicit terminal state. Proc International Joint Confernece on Neural Networks (IJCNN '98), Anchorage, Alaska, 1998
10. Bellman RE. Dynamic Programming, Princeton University Press, Princeton, NJ, 1957
11. Bertsekas DP. Dynamic Programming, Prentice-Hall, Englewood Cliffs, NJ, 1987
12. Riedmiller M. Learning to control dynamic systems. In: R Trappl, editor, Proc 13th European Meeting on Cybernetics and Systems Research (EMCSR '96), Vienna, 1996
13. Sutton RS. Learning to predict by the methods of temporal differences. Machine Learning 1988; (3): 9-44
14. Watkins CJ. Learning from Delayed Rewards. Phd thesis, Cambridge University, 1989
15. Riedmiller M. Generating continuous control signals for reinforcement controllers using dynamic output elements. European Symposium on Artificial Neural Networks (ESANN '97), Bruges, 1997
16. Föllinger O. Nichtlineare Regelungen, Oldenbourg, 7th edition, 1993