메뉴 건너뛰기




Volumn 3, Issue 6, 1990, Pages 671-692

A stochastic reinforcement learning algorithm for learning real-valued functions

Author keywords

Associative reinforcement learning; Learning algorithm; Neural networks; Neurocontrol; Real valued functions; Robotics; Shaping; Stochastic automata

Indexed keywords

COMPUTER PROGRAMMING--ALGORITHMS; LEARNING SYSTEMS; ROBOTS--MANIPULATORS;

EID: 0025600638     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/0893-6080(90)90056-Q     Document Type: Article
Times cited : (207)

References (31)
  • 4
    • 0003630733 scopus 로고
    • Learning and problem solving with multilayer connectionist systems
    • University of Massachusetts, Amherst
    • (1986) Ph.D. dissertation
    • Anderson1
  • 7
    • 0022213383 scopus 로고
    • Learning by statistical cooperation of self-interested neuron-like computing elements
    • (1985) Human Neurobiology , vol.4 , pp. 229-256
    • Barto1
  • 11
    • 84910776456 scopus 로고    scopus 로고
    • Barto, A. G., Sutton, R. S., & Watkins, C. (to appear). Prediction, control, and learning. In M. Gabriel and J. W. Moore (Eds.), Learning and computational neuroscience. Cambridge, MA: The MIT Press.
  • 16
    • 0012083286 scopus 로고
    • A stochastic algorithm for learning real-valued functions via reinforcement feedback
    • Dept. of Computer and Info. Sciences, University of Massachusetts, Amherst
    • (1988) COINS Technical Report 88–91
    • Gullapalli1
  • 28
    • 0003617454 scopus 로고
    • Temporal aspects of credit assignment in reinforcement learning
    • University of Massachusetts, Amherst
    • (1984) Ph.D. dissertation
    • Sutton1
  • 31
    • 0012076854 scopus 로고
    • Reinforcement learning in connectionist networks: A mathematical analysis
    • University of California, La Jolla, San Diego, Institute for Cognitive Science
    • (1986) Technical Report 8605
    • Williams1


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.