CHQ: A multi-agent reinforcement learning scheme for partially observable Markov decision processes

IEICE Transactions on Information and Systems

Volumn E88-D, Issue 5, 2005, Pages 1004-1011

  Osada, Hiroshi ^a   Fujita, Satoshi ^b  

^a TOYOTA INDUSTRIES CORPORATION   (Japan)

^b HIROSHIMA UNIVERSITY   (Japan)

Author keywords

Multi agent system; Partially observable MDP; Q learning; Reinforcement learning

Indexed keywords

DECISION SUPPORT SYSTEMS; LEARNING SYSTEMS; MARKOV PROCESSES; PROBABILITY;

PARTIALLY OBSERVABLE MDP; Q-LEARNING; REINFORCEMENT LEARNING; STATE TRANSITIONS;

MULTI AGENT SYSTEMS;

EID: 24144454723     PISSN: 09168532     EISSN: None     Source Type: Journal    
DOI: 10.1093/ietisy/e88-d.5.1004     Document Type: Conference Paper

References (12)

1. S.A. Barnett, Instinct and Intelligence: Behavior of Animals and Man, Prentice-Hall, Englewood Cliffs, NJ, 1967.
2. M. Benda, V. Jagannathan, and R. Dodhiawalla, "On optimal cooperation of knowledge sources,"Technical Report, BCS-G2010-28, Boeing AI Center, 1985.
3. R.H. Guttman, A.C. Moukas, and P. Maes, "Agent-mediated electronic commerce: A survey,"Knowledge Engineering Review, vol.13, no.2, pp.147-159, 1998.
4. L. Lin, Reinforcement Learning for Robots Using Neural Networks, PhD thesis, Carnegie Mellon University, Pittsburgh, 1993.
5. A. Moore and C.G. Atkeson, "Prioritized sweeping: Reinforcement learning with less data and less time,"Mach. Learn., vol. 13, pp.103-130, 1993.
6. R.S. Sutton, "Learning to predict by the method of temporal differences,"Mach. Learn., vol.3, pp.9-44, 1998.
7. R.S. Sutton and A.G. Barto, "Reinforcement learning: An introduction,"in A Bradford Book, MIT Press, 1998.
8. N. Tinbergen, Animal Behavior, Little Brown & Company, 1974.
9. C.J.C.H. Watkins and P. Dayan, "Technical note: Q-Learning, "Mach. Learn., vol.8, pp.279-292, 1992.
10. M. Wiering and J. Schmidhuber, "HQ-learning,"Adaptive Behavior, vol.6, no.2, 1997.
11. Y. Yamashiro, A. Ueno, and H. Takeda, "Delayed reward-based genetic algorithms for partially observable Markov decision problems,"IEICE Trans. Inf. & Syst. (Japanese Edition), vol.J84-D-l, no.12, pp.1635-1647, Dec. 2001.
12. URL: http://nssdc.gsfc.nasa.gov/planetary/mesur.html