Reinforcement learning for problems with symmetrical restricted states

Robotics and Autonomous Systems

Volumn 56, Issue 9, 2008, Pages 717-727

  Kamal, M A S ^a   Murata, Junichi ^a  

^a KYUSHU UNIVERSITY   (Japan)

Author keywords

Elevator group control system; High dimensionality; Reinforcement learning; Symmetry

Indexed keywords

EDUCATION; OPTICAL FILTERS; REINFORCEMENT LEARNING; STANDARDS;

ACTION SELECTION; ELEVATOR GROUP CONTROL SYSTEM; HIGH DIMENSIONALITY; REINFORCEMENT LEARNING METHODS; SIMULATION RESULTS; SYMMETRY; VALUE FUNCTIONS;

REINFORCEMENT;

EID: 49649084490     PISSN: 09218890     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.robot.2008.01.004     Document Type: Article

References (24)

1. Boyan J.A., and Moore A.W. Generalization in reinforcement learning: Safely approximating the value function. Advances in Neural Information Processing Systems vol. 7 (1995), MIT Press, Cambridge 369-376
2. Sutton R.S. Generalization in reinforcement learning: Successful examples using sparse coding. Advances in Neural Information Processing Systems vol. 8 (1996), MIT Press, Cambridge 1038-1044
3. P. Stone, R.S. Sutton, Scalling reinforcement learning toward robocup soccer, in: Proc. of the 18th Int. Conf. on Machine learning, 2001
4. Barto A.G., and Mahadevan S. Recent advances in hierarchical reinforcement learning. Discrete Event Dynamic Systems 13 4 (2003) 41-77
5. Kamal M.A.S., Murata J., and Hirasawa K. Task-oriented reinforcement learning for continuing task in dynamic environment. Research Reports on Information Science and Electrical Engineering of Kyushu University 9 1 (2004) 7-12
6. Boutilier C., Dearden R., and Goldszmidt M. Stochastic dynamic programming with factored representations. Artificial Intelligence 121 (2000) 49-107
7. B. Hengst, Generating hierarchical structure in reinforcement learning from state variables, in: PRICAI 2000 Topics in Artificial Intelligence, 2000, pp. 533-543
8. Connel J., and Mahadevan S. Rapid task learning for real robot. Robot Learning (1993), Kluwer Academic Publishers
9. M.A.S. Kamal, J. Murata, K. Hirasawa, Task-oriented reinforcement learning for continuous tasks in dynamic environment, in: Proc. of the Conf. of Soceity of Instrument and Control Eng., 2002, pp. 932-935
10. M.A.S. Kamal, J. Murata, K. Hirasawa, Task-oriented multiagent reinforcement learning control for a real time high-dimensional problem, in: Proc. Int. Symposium on Artificial Life and Robotics, vol. 2, 2003, pp. 353-356
11. M. Zinkevich, T. Balch, Symmetry in Markov decision process and their implication for single agent and multi-agent learning, in: Proc. of the 18th Int. Conf. on Machine learning, 2001, pp. 632-640
12. B. Ravindran, A.G. Barto, SMDP homomorphisms: An algebraic approach to abstraction in semi Markov decision processes, in: Proc. of the 18th Int. Joint Conf. on Artificial Intel., IJCAI 2003, pp. 1011-1016
13. M. Kearns, D. Koller, Efficient reinforcement learning in factored MDPs, in: Proc. of the 16th Int. Joint Conf. on Artificial Intel., IJCAI, 1999, pp. 740-747
14. Brian Sallans, Reinforcement learning for factored Markov decision process, Ph.D. Dissertation, Dept. of Computer Science, Torento University, 2002
15. B. Ravindran, An algebraic approach to abstraction in reinforcement learning, Doctoral Dissertation, University of Massachusetts, 2004
16. M.A.S. Kamal, J. Murata, Reinforcement learning for high-dimensional problems with symmetrical actions, in: Proc. of Annual Conf. of IEEE Systems Man and Cybernetics, IEEE SMC, The Hague, Netherlands, October 2004, pp. 6192-6197
17. Sutton R.S., and Barto A.G. Reinforcement Learning: An Introduction (1998), MIT Press
18. Kaelbling L.P., Litman M.L., and Moore A.W. Reinforcement learning: A survey. Journal of Artificial Intelligence Research 4 (1996) 237-285
19. Watkins C.J.C.H., and Dayan P. Q-learning. Machine Learning 8 (1992) 279-292
20. Tsitsiklis J.N. Asynchronous stochastic approximation and Q-learning. Machine Learning 16 (1994) 185-202
21. M. Tan, Multi-agent reinforcement learning: Independent vs. cooperative agents, in: Proc. Int. Conf. on Machine Learning, 1993, pp. 330-337
22. Crites R.H., and Barto A.G. Elevator group control using multiple reinforcement learning agents. Machine Learning 33 2-3 (1998) 235-262
23. Levy D., Yadin M., and Alexandrovitz A. Optimal control of elevators. International Journal of Systems Science 8 (1977) 301-320
24. Kamal M.A.S., Murata J., and Hirasawa K. Elevator group control using multiagent task-oriented reinforcement learning. Transactions of IEE Japan, Part C 125 7 (2005) 1140-1146