Tug-of-war model for the two-bandit problem: Nonlocally-correlated parallel exploration via resource conservation

BioSystems

Volumn 101, Issue 1, 2010, Pages 29-36

  Kim, Song Ju ^a,b   Aono, Masashi ^a,b   Hara, Masahiko ^a,b  

^a RIKEN   (Japan)

^b Hanyang University   (South Korea)

Author keywords

Amoeba based computing; Bio inspired computing; Multi armed bandit problem; Reinforcement learning

Indexed keywords

ACCURACY ASSESSMENT; ALGORITHM; DECISION MAKING; EFFICIENCY MEASUREMENT; MICROBIAL ACTIVITY; MODEL; NUMERICAL MODEL; RESOURCE ALLOCATION; THEORETICAL STUDY;

ACCURACY; ALGORITHM; ARTICLE; DECISION MAKING; ENVIRONMENTAL PROTECTION; MOLECULAR MODEL; NONHUMAN; OSCILLATION; PHYSARUM POLYCEPHALUM; REINFORCEMENT; TUG OF WAR MODEL; BIOMIMETICS; CELL SIZE; DATA MINING; PHYSARUM; PHYSIOLOGY; PROCEDURES; STATISTICS;

MYXOGASTRIA; PHYSARUM;

ALGORITHMS; BIOMIMETICS; CELL SIZE; CONSERVATION OF NATURAL RESOURCES; DATA MINING; PHYSARUM; STATISTICS AS TOPIC;

EID: 77953609815     PISSN: 03032647     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.biosystems.2010.04.002     Document Type: Article

References (21)

1. Agrawal R. Sample mean based index policies with O(logn) regret for the multi-armed bandit problem. Advances in Applied Probability 1995, 27:1054-1078.
2. Aono M., Hara M., Aihara K. Amoeba-based neurocomputing with chaotic dynamics. Communications of the ACM 2007, 50(9):69-72.
3. Aono M., Hara M. Spontaneous deadlock breaking on amoeba-based neurocomputer. BioSystems 2008, 91:83-93.
4. Aono M., Hirata Y., Hara M., Aihara K. Amoeba-based chaotic neurocomputing: combinatorial optimization by coupled biological oscillators. New Generation Computing 2009, 27:129-157.
5. Aono M., Hirata Y., Hara Y., Aihara K. Resource-competing oscillator network as a model of amoeba-based neurocompute. Unconventional Computation. Lecture Notes in Computer Science, vol. 5715 2009, 56-69. Springer. C. Calude (Ed.).
6. Auer P., Cesa-Bianchi N., Fischer P. Finite-time analysis of the multiarmed bandit problem. Machine Learning 2002, 47:235-256.
7. Cohen J., McClure S., Yu A. Should I stay or should I go? How the human brain manages the trade-off between exploitation and exploration. Philosophical Transactions of the Royal Society B 2007, 362(1481):933-942.
8. Daw N., O'Doherty J., Dayan P., Seymour B., Dolan R. Cortical substrates for exploratory decisions in humans. Nature 2006, 441:876-879.
9. Gittins J., Jones D. A dynamic allocation index for the sequential design of experiments. Progress in Statistics 1974, 241-266. North Holland. J. Gans (Ed.).
10. Gittins J. Bandit processes and dynamic allocation indices. Journal of the Royal Statistical Society B 1979, 41:148-177.
11. Kim S.-J., Aono M., Hara M. Tug-of-war model for two-bandit problem. Unconventional Computation. Lecture Notes in Computer Science, vol. 5715 2009, 289. Springer. C. Calude (Ed.).
12. Kim S.-J., Aono M., Hara M. Tug-of-war model for multi-armed bandit problem. Unconventional Computation. to be published in Lecture Notes in Computer Science 2010, Springer. C. Calude (Ed.).
13. Lai T., Robbins H. Asymptotically efficient adaptive allocation rules. Advances in Applied Mathematics 1985, 6:4-22.
14. Nakagaki T., Yamada H., Toth A. Maze-solving by an amoeboid organism. Nature 2000, 407:470.
15. Nakagaki T., Iima M., Ueda T., Nishiura Y., Saigusa T., Tero A., Kobayashi R., Showalter K. Minimum-risk path finding by an adaptive amoebal network. Physical Review Letters 2007, 99:068104.
16. Robbins H. Some aspects of the sequential design of experiments. Bulletin of the American Mathematical Society 1952, 58:527-536.
17. Saigusa T., Tero A., Nakagaki T., Kuramoto Y. Amoebae anticipate periodic events. Physical Review Letters 2008, 100:018101.
18. Sutton R., Barto A. Reinforcement Learning: An Introduction 1998, MIT Press.
19. Tero A., Kobayashi R., Nakagaki T. Physarum solver: a biologically inspired method of road-network navigation. Physica A 2006, 363:115-119.
20. Thompson W. On the likelihood that one unknown probability exceeds another in view of the evidence of two samples. Biometrika 1933, 25:285-294.
21. Vermorel J., Mohri M. Multi-armed bandit algorithms and empirical evaluation. 16th European Conference on Machine Learning. Lecture Notes in Artificial Intelligence, vol. 3720 2005, 437-448. Springer. J. Gama (Ed.).