Meta-learning in reinforcement learning

Neural Networks

Volumn 16, Issue 1, 2003, Pages 5-9

  Schweighofer, Nicolas ^a   Doya, Kenji ^a,b  

^a JAPAN SCIENCE AND TECHNOLOGY AGENCY   (Japan)

^b ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

Author keywords

Dopamine; Dynamic environment; Meta learning; Meta parameters; Neuromodulation; Reinforcement learning; TD error

Indexed keywords

ADAPTIVE SYSTEMS; ALGORITHMS; MARKOV PROCESSES; ROBUSTNESS (CONTROL SYSTEMS); SIGNAL ENCODING;

REINFORCEMENT LEARNING;

LEARNING SYSTEMS;

DOPAMINE;

ALGORITHM; ARTICLE; DECISION MAKING; DOPAMINERGIC ACTIVITY; DOPAMINERGIC NERVE CELL; ENVIRONMENTAL FACTOR; LEARNING; MENTAL TASK; NEUROMODULATION; NONLINEAR SYSTEM; PRIORITY JOURNAL; PROBABILITY; REINFORCEMENT; SIMULATION; TASK PERFORMANCE; TIME;

ALGORITHMS; ARTIFICIAL INTELLIGENCE; DECISION THEORY; MARKOV CHAINS; REINFORCEMENT (PSYCHOLOGY); STOCHASTIC PROCESSES;

EID: 0037258402     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(02)00228-9     Document Type: Article

References (17)

1. Aston-Jones G., Bloom F.E. Activity of norepinephrine-containing locus coeruleus neurons in behaving rats anticipates fluctuations in the sleep-waking cycle. Journal of Neuroscience. 1:(8):1981;876-886.
2. Daw N.D., Kakade S., Dayan P. Opponent interactions between serotonin and dopamine. Neural Networks. 15:2002;603-616.
3. Day J., Fibiger H.C. Dopaminergic regulation of cortical acetylcholine release: effects of dopamine receptor agonists. Neuroscience. 54:(3):1993;643-648.
4. Doya K. Reinforcement learning in continuous time and space. Neural Computations. 12:(1):2000;219-245.
5. Doya K. Metalearning and neuromodulation. Neural Networks. 15:2002;495-506.
6. Gullapalli V. A stochastic reinforcement learning algorithm for learning real-valued functions. Neural Networks. 3:1990;671-692.
7. Haj-Dahmane S. D2-like dopamine receptor activation excites rat dorsal raphe 5-HT neurons in vitro. European Journal of Neuroscience. 14:(1):2001;125-134.
8. Ishii S., Yoshida W., Yoshimoto J. Control of exploitation-exploration meta-parameters in reinforcement learning. Neural Networks. 15:2002;665-687.
9. Jacobs B.L., Fornal C.A. 5-HT and motor control: a hypothesis. Trends in Neuroscience. 16:(9):1993;346-352.
10. Littman, M. L., Dean, T. L., et al (1995). On the complexity of solving Markov decision problems. Eleventh International Conference on Uncertainty in Artificial Intelligence.
11. Maeda T., Kojima Y., Arai R., Fujimiya M., Kimura H., Kitahama A., Geffard M. Monoaminergic interaction in the central nervous system: a morphological analysis in the locus coeruleus of the rat. Compartative Biochemistry and Physiology C. 98:(1):1991;193-202.
12. Schultz W. Predictive reward signal of dopamine neurons. Journal of Neurophysiology. 80:(1):1998;1-27.
13. Schweighofer N., Arbib M.A. A model of cerebellar metaplasticity. Learning Memory. (4):1998;421-428.
14. Solomon R.L., Corbit J.D. An opponent process theory of motivation. I. Temporal dynamics of affect. Psychological Review. 81:1974;119-145.
15. Sutton, R (1992). Adapting bias by gradient descent: an incremental version of the delta-bar-delta. Tenth National Conference on Artificial Intelligence. Cambridge, MA: MIT Press.
16. Tanaka S., Doya K., Okada G., Ueda K., Okamoto Y., Yamawaki S. Functional MRI study of short-term and long-term prediction of reward. Proceedings of the Eighth International Conference on Functional Mapping of the Human Brain, Sendai, Japan. 2002;1062.
17. Thrun S.B. White D.A., Dofge D.A. The role of exploration in learning control. Handbook of intelligent control: Neural, fuzzy, and adaptive approaches. 1992;Van Nostrand, Florence, Kentucky.