메뉴 건너뛰기




Volumn 70, Issue 1-3, 2006, Pages 21-34

Influence zones: A strategy to enhance reinforcement learning

Author keywords

Instantaneous topological map; Learning acceleration; Reinforcement learning; Self organizing map

Indexed keywords

ESTIMATION; LEARNING ALGORITHMS; LEARNING SYSTEMS; SELF ORGANIZING MAPS; TOPOLOGY;

EID: 33750404375     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2006.07.010     Document Type: Article
Times cited : (14)

References (32)
  • 1
    • 0003787146 scopus 로고
    • Princeton University Press, Princeton, NJ
    • Bellman R. Dynamic Programming (1957), Princeton University Press, Princeton, NJ
    • (1957) Dynamic Programming
    • Bellman, R.1
  • 3
    • 0346342550 scopus 로고    scopus 로고
    • A topological reinforcement learning agent for navigation
    • Braga A.P.S., and Araújo A.F.R. A topological reinforcement learning agent for navigation. Neural Comput. Appl. 12 3-4 (2003) 220-236
    • (2003) Neural Comput. Appl. , vol.12 , Issue.3-4 , pp. 220-236
    • Braga, A.P.S.1    Araújo, A.F.R.2
  • 4
    • 85135470835 scopus 로고
    • A growing neural gas network learns topologies
    • Fritzke B. A growing neural gas network learns topologies. Adv. Neural Inform. Process. Syst. 7 (1995) 625-632
    • (1995) Adv. Neural Inform. Process. Syst. , vol.7 , pp. 625-632
    • Fritzke, B.1
  • 5
    • 0012532267 scopus 로고    scopus 로고
    • Unsupervised ontogenetic networks
    • Fiesler E., and Beale R. (Eds), Institute of Physics Publishing and Oxford University Press
    • Fritzke B. Unsupervised ontogenetic networks. In: Fiesler E., and Beale R. (Eds). Handbook of Neural Computation (1996), Institute of Physics Publishing and Oxford University Press
    • (1996) Handbook of Neural Computation
    • Fritzke, B.1
  • 7
    • 33750393529 scopus 로고    scopus 로고
    • A. Großmann, Continual learning for mobile robots, Ph.D. thesis, School of Computer Science, The University of Birmingham, Birmingham, UK, 2001.
  • 8
    • 85131710558 scopus 로고    scopus 로고
    • J. Jockusch, H. Ritter, An instantaneous topological mapping model for correlated stimuli. Proceedings of the IJCNN'99, 1999, pp. 445.
  • 11
    • 3142715411 scopus 로고    scopus 로고
    • Three-dimensional map building for mobile robot navigation environments using a self-organizing neural network
    • Kim M.Y., and Cho H. Three-dimensional map building for mobile robot navigation environments using a self-organizing neural network. J. Robot. Syst. 21 6 (2004) 323-343
    • (2004) J. Robot. Syst. , vol.21 , Issue.6 , pp. 323-343
    • Kim, M.Y.1    Cho, H.2
  • 12
    • 0029751419 scopus 로고    scopus 로고
    • The effect of representation and knowledge on goal-directed exploration with reinforcement learning algorithms
    • Koenig S., and Simmons R.G. The effect of representation and knowledge on goal-directed exploration with reinforcement learning algorithms. Mach. Learn. 22 (1996) 227-250
    • (1996) Mach. Learn. , vol.22 , pp. 227-250
    • Koenig, S.1    Simmons, R.G.2
  • 14
    • 0028204732 scopus 로고
    • Topology representing networks
    • Martinetz T., and Schulten K. Topology representing networks. Neural Networks 7 3 (1994) 507-522
    • (1994) Neural Networks , vol.7 , Issue.3 , pp. 507-522
    • Martinetz, T.1    Schulten, K.2
  • 16
    • 33750393758 scopus 로고    scopus 로고
    • R.A. McCallum, Using transitional proximity for faster reinforcement learning, Proceedings of the Ninth International Conference on Machine Learning, 1992, pp. 316-321.
  • 17
    • 0030171602 scopus 로고    scopus 로고
    • Rapid, safe, and incremental learning of navigation strategies
    • Milán J., and del R. Rapid, safe, and incremental learning of navigation strategies. IEEE Trans. Syst., Man, Cybernet. 26 (1996) 408-420
    • (1996) IEEE Trans. Syst., Man, Cybernet. , vol.26 , pp. 408-420
    • Milán, J.1    del, R.2
  • 20
    • 0027684215 scopus 로고
    • Prioritized sweeping: reinforcement learning with less data and less time
    • Moore A.W., and Atkeson C.G. Prioritized sweeping: reinforcement learning with less data and less time. Mach. Learn. 13 (1993) 103-130
    • (1993) Mach. Learn. , vol.13 , pp. 103-130
    • Moore, A.W.1    Atkeson, C.G.2
  • 21
    • 0000955979 scopus 로고    scopus 로고
    • Incremental multi-step Q-learning
    • Peng J., and Williams R.J. Incremental multi-step Q-learning. Mach. Learn. 22 (1996) 283-290
    • (1996) Mach. Learn. , vol.22 , pp. 283-290
    • Peng, J.1    Williams, R.J.2
  • 22
    • 33750392533 scopus 로고    scopus 로고
    • C.H.C. Ribeiro, Aspects of the behaviour of a learning agent in control tasks, Ph.D. thesis, Imperial College of Science, Technology and Medicine, University of London, 1998.
  • 23
    • 0036570250 scopus 로고    scopus 로고
    • Reinforcement learning agents
    • Ribeiro C.H.C. Reinforcement learning agents. Artif. Intell. Rev. 17 (2002) 223-250
    • (2002) Artif. Intell. Rev. , vol.17 , pp. 223-250
    • Ribeiro, C.H.C.1
  • 25
    • 33750397173 scopus 로고    scopus 로고
    • G.A. Rummery, Problem solving with reinforcement learning, Ph.D. thesis, Cambridge University, 1995.
  • 27
    • 0036790898 scopus 로고    scopus 로고
    • Applications of the self-organising map to reinforcement learning
    • Smith A.J. Applications of the self-organising map to reinforcement learning. Neural Networks 15 8-9 (2002) 1107-1124
    • (2002) Neural Networks , vol.15 , Issue.8-9 , pp. 1107-1124
    • Smith, A.J.1
  • 28
    • 0012929784 scopus 로고
    • Dyna, an integrated architecture for learning, planning, and reacting
    • ACM Press
    • Sutton R.S. Dyna, an integrated architecture for learning, planning, and reacting. SIGART Bull. 2 (1991) 160-163 ACM Press
    • (1991) SIGART Bull. , vol.2 , pp. 160-163
    • Sutton, R.S.1
  • 30
    • 0031341345 scopus 로고    scopus 로고
    • Neural reinforcement learning for behaviour synthesis
    • Touzet C. Neural reinforcement learning for behaviour synthesis. Robot. Autonom. Syst. 22 3-4 (1997) 251-281
    • (1997) Robot. Autonom. Syst. , vol.22 , Issue.3-4 , pp. 251-281
    • Touzet, C.1
  • 31
    • 33750392301 scopus 로고    scopus 로고
    • C.J.C.H. Watkins, Learning from delayed rewards, Ph.D. thesis, King's College, Cambridge, 1989.


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.