메뉴 건너뛰기




Volumn 2015-January, Issue , 2015, Pages 2125-2133

Variational information maximisation for intrinsically motivated reinforcement learning

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; ARTIFICIAL INTELLIGENCE; COMPLEX NETWORKS; COMPUTATIONAL COMPLEXITY; DIGITAL STORAGE; INFORMATION SCIENCE; LEARNING SYSTEMS; OPTIMIZATION; REINFORCEMENT LEARNING; STOCHASTIC SYSTEMS; VARIATIONAL TECHNIQUES;

EID: 84965128263     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper
Times cited : (381)

References (29)
  • 1
    • 38149077590 scopus 로고    scopus 로고
    • The IM algorithm: A variational approach to information maximization
    • Barber, D. and Agakov, F. The IM algorithm: a variational approach to information maximization. In NIPS, volume 16, pp. 201, 2004.
    • (2004) NIPS , vol.16 , pp. 201
    • Barber, D.1    Agakov, F.2
  • 2
    • 0032184953 scopus 로고    scopus 로고
    • Mutual information, Fisher information, and population coding
    • Brunel, N. and Nadal, J. Mutual information, Fisher information, and population coding. Neural Computation, 10(7):1731-1757, 1998.
    • (1998) Neural Computation , vol.10 , Issue.7 , pp. 1731-1757
    • Brunel, N.1    Nadal, J.2
  • 5
    • 80052250414 scopus 로고    scopus 로고
    • Adaptive subgradient methods for online learning and stochastic optimization
    • Duchi, J., Hazan, E., and Singer, Y. Adaptive subgradient methods for online learning and stochastic optimization. The Journal of Machine Learning Research, 12:2121-2159, 2011.
    • (2011) The Journal of Machine Learning Research , vol.12 , pp. 2121-2159
    • Duchi, J.1    Hazan, E.2    Singer, Y.3
  • 7
    • 0141521533 scopus 로고    scopus 로고
    • The kernel mutual information
    • Gretton, A., Herbrich, R., and Smola, A. J. The kernel mutual information. In ICASP, volume 4, pp. IV-880, 2003.
    • (2003) ICASP , vol.4 , pp. IV-880
    • Gretton, A.1    Herbrich, R.2    Smola, A.J.3
  • 8
    • 84864068293 scopus 로고    scopus 로고
    • Bayesian surprise attracts human attention
    • Itti, L. and Baldi, P. F. Bayesian surprise attracts human attention. In NIPS, pp. 547-554, 2005.
    • (2005) NIPS , pp. 547-554
    • Itti, L.1    Baldi, P.F.2
  • 9
    • 0001837853 scopus 로고    scopus 로고
    • Improving the mean field approximation via the use of mixture distributions
    • Jaakkola, T. S. and Jordan, M. I. Improving the mean field approximation via the use of mixture distributions. In Learning in graphical models, pp. 163-173. 1998.
    • (1998) Learning in Graphical Models , pp. 163-173
    • Jaakkola, T.S.1    Jordan, M.I.2
  • 10
    • 79952169043 scopus 로고    scopus 로고
    • Empowerment for continuous agent-environment systems
    • Jung, T., Polani, D., and Stone, P. Empowerment for continuous agent-environment systems. Adaptive Behavior, 19(1):16-39, 2011.
    • (2011) Adaptive Behavior , vol.19 , Issue.1 , pp. 16-39
    • Jung, T.1    Polani, D.2    Stone, P.3
  • 12
    • 84905695541 scopus 로고    scopus 로고
    • Evolving deep unsupervised convolutional networks for vision-based reinforcement learning
    • Koutník, J., Schmidhuber, J., and Gomez, F. Evolving deep unsupervised convolutional networks for vision-based reinforcement learning. In GECCO, pp. 541-548, 2014.
    • (2014) GECCO , pp. 541-548
    • Koutník, J.1    Schmidhuber, J.2    Gomez, F.3
  • 15
    • 84924051598 scopus 로고    scopus 로고
    • Human-level control through deep reinforcement learning
    • Mnih, V., Kavukcuoglu, K., and Silver, D., et al. Human-level control through deep reinforcement learning. Nature, 518(7540):529-533, 2015.
    • (2015) Nature , vol.518 , Issue.7540 , pp. 529-533
    • Mnih, V.1    Kavukcuoglu, K.2    Silver, D.3
  • 16
    • 27944459371 scopus 로고    scopus 로고
    • Finding useful questions: On Bayesian diagnosticity, probability, impact, and information gain
    • Nelson, J. D. Finding useful questions: on Bayesian diagnosticity, probability, impact, and information gain. Psychological review, 112(4):979, 2005.
    • (2005) Psychological Review , vol.112 , Issue.4 , pp. 979
    • Nelson, J.D.1
  • 17
    • 0141596576 scopus 로고    scopus 로고
    • Policy invariance under reward transformations: Theory and application to reward shaping
    • Ng, Andrew Y, Harada, Daishi, and Russell, Stuart. Policy invariance under reward transformations: Theory and application to reward shaping. In ICML, 1999.
    • (1999) ICML
    • Ng, A.Y.1    Harada, D.2    Russell, S.3
  • 20
    • 84901395918 scopus 로고    scopus 로고
    • Changing the environment based on empowerment as intrinsic motivation
    • Salge, C., Glackin, C., and Polani, D. Changing the environment based on empowerment as intrinsic motivation. Entropy, 16(5):2789-2819, 2014.
    • (2014) Entropy , vol.16 , Issue.5 , pp. 2789-2819
    • Salge, C.1    Glackin, C.2    Polani, D.3
  • 22
    • 77956578648 scopus 로고    scopus 로고
    • Formal theory of creativity, fun, and intrinsic motivation (1990-2010)
    • Schmidhuber, J. Formal theory of creativity, fun, and intrinsic motivation (1990-2010). IEEE Trans. Autonomous Mental Development, 2(3):230-247, 2010.
    • (2010) IEEE Trans. Autonomous Mental Development , vol.2 , Issue.3 , pp. 230-247
    • Schmidhuber, J.1
  • 23
    • 84899031920 scopus 로고    scopus 로고
    • Intrinsically motivated reinforcement learning
    • Singh, S. P., Barto, A. G., and Chentanez, N. Intrinsically motivated reinforcement learning. In NIPS, 2005.
    • (2005) NIPS
    • Singh, S.P.1    Barto, A.G.2    Chentanez, N.3
  • 24
    • 84865114997 scopus 로고    scopus 로고
    • An information-theoretic approach to curiosity-driven reinforcement learning
    • Still, S. and Precup, D. An information-theoretic approach to curiosity-driven reinforcement learning. Theory in Biosciences, 131(3):139-148, 2012.
    • (2012) Theory in Biosciences , vol.131 , Issue.3 , pp. 139-148
    • Still, S.1    Precup, D.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.