메뉴 건너뛰기




Volumn 7, Issue NOV, 2013, Pages

Which is the best intrinsic motivation signal for learning multiple skills?

Author keywords

Competence acquisition; Hierarchical architecture; Intrinsic motivations; Learning signals; Multiple skills; Reinforcement learning; Simulated robot

Indexed keywords

ARTICLE; COMPETENCE; HYPOTHESIS; KINEMATICS; LEARNING; MOTIVATION; REINFORCEMENT; SIMULATION; SKILL;

EID: 84902548432     PISSN: None     EISSN: 16625218     Source Type: Journal    
DOI: 10.3389/fnbot.2013.00022     Document Type: Article
Times cited : (66)

References (40)
  • 1
    • 84899674335 scopus 로고    scopus 로고
    • Intrinsically Motivated Learning in Natural and Artificial Systems
    • doi: 10.1007/978-3-642-32375-1 (eds.).Berlin: Springer-Verlag.
    • Baldassarre, G., and Mirolli, M. (eds.). (2013a). Intrinsically Motivated Learning in Natural and Artificial Systems. Berlin: Springer-Verlag. doi: 10.1007/978-3-642-32375-1
    • (2013)
    • Baldassarre, G.1    Mirolli, M.2
  • 2
    • 84904871924 scopus 로고    scopus 로고
    • Deciding which skill to learn when: temporal-difference competence-based intrinsic motivation (TD-CB-IM)
    • eds G. Baldassarre and M. Mirolli (Berlin: Springer-Verlag)
    • Baldassarre, G., and Mirolli, M. (2013b). "Deciding which skill to learn when: temporal-difference competence-based intrinsic motivation (TD-CB-IM)," in Intrinsically Motivated Learning in Natural and Artificial Systems, eds G. Baldassarre and M. Mirolli (Berlin: Springer-Verlag), 257-278.
    • (2013) Intrinsically Motivated Learning in Natural and Artificial Systems , pp. 257-278
    • Baldassarre, G.1    Mirolli, M.2
  • 4
    • 77955701366 scopus 로고    scopus 로고
    • R-iac: robust intrinsically motivated exploration and active learning
    • doi: 10.1109/TAMD.2009.2037513
    • Baranes, A., and Oudeyer, P. Y. (2009). R-iac: robust intrinsically motivated exploration and active learning. IEEE Trans. Auton. Ment. Dev. 1, 155-169. doi: 10.1109/TAMD.2009.2037513
    • (2009) IEEE Trans. Auton. Ment. Dev. , vol.1 , pp. 155-169
    • Baranes, A.1    Oudeyer, P.Y.2
  • 5
    • 84870239334 scopus 로고    scopus 로고
    • Active learning of inverse models with intrinsically motivated goal exploration in robots
    • doi: 10.1016/j.robot.2012.05.008
    • Baranes, A., and Oudeyer, P.-Y. (2013). Active learning of inverse models with intrinsically motivated goal exploration in robots. Robot. Auton. Syst. 61, 49-73. doi: 10.1016/j.robot.2012.05.008
    • (2013) Robot. Auton. Syst. , vol.61 , pp. 49-73
    • Baranes, A.1    Oudeyer, P.-Y.2
  • 7
    • 0020970738 scopus 로고
    • Neuron-like adaptive elements that can solve difficult learning control problems
    • doi: 10.1109/TSMC.1983.6313077
    • Barto, A., Sutton, R., and Anderson, C. (1983). Neuron-like adaptive elements that can solve difficult learning control problems. IEEE Trans. Syst. Man Cybernet. 13, 834-846. doi: 10.1109/TSMC.1983.6313077
    • (1983) IEEE Trans. Syst. Man Cybernet. , vol.13 , pp. 834-846
    • Barto, A.1    Sutton, R.2    Anderson, C.3
  • 9
    • 0033629916 scopus 로고    scopus 로고
    • Reinforcement learning in continuous time and space
    • doi: 10.1162/089976600300015961
    • Doya, K. (2000). Reinforcement learning in continuous time and space. Neural Comput. 12, 219-245. doi: 10.1162/089976600300015961
    • (2000) Neural Comput. , vol.12 , pp. 219-245
    • Doya, K.1
  • 10
    • 77649339615 scopus 로고    scopus 로고
    • Novelty-related motivation of anticipation and exploration by dopamine (nomad): implications for healthy aging
    • doi: 10.1016/j.neubiorev.2009.08.006
    • Duzel, E., Bunzeck, N., Guitart-Masip, M., and Duzel, S. (2010). Novelty-related motivation of anticipation and exploration by dopamine (nomad): implications for healthy aging. Neurosci. Biobehav. Rev. 34, 660-669. doi: 10.1016/j.neubiorev.2009.08.006
    • (2010) Neurosci. Biobehav. Rev. , vol.34 , pp. 660-669
    • Duzel, E.1    Bunzeck, N.2    Guitart-Masip, M.3    Duzel, S.4
  • 11
    • 0009762657 scopus 로고
    • Learning and satiation of response in intrinsically motivated complex puzzle performance by monkeys
    • doi: 10.1037/h0058114
    • Harlow, H. F. (1950). Learning and satiation of response in intrinsically motivated complex puzzle performance by monkeys. J. Comp. Physiol. Psychol. 43, 289-294. doi: 10.1037/h0058114
    • (1950) J. Comp. Physiol. Psychol. , vol.43 , pp. 289-294
    • Harlow, H.F.1
  • 12
    • 84903152232 scopus 로고    scopus 로고
    • Intrinsically motivated affordance discovery and modeling
    • eds G. Baldassarre and M. Mirolli (Berlin: Springer-Verlag)
    • Hart, S., and Grupen, R. (2013). "Intrinsically motivated affordance discovery and modeling," in Intrinsically Motivated Learning in Natural and Artificial Systems, eds G. Baldassarre and M. Mirolli (Berlin: Springer-Verlag), 279-300.
    • (2013) Intrinsically Motivated Learning in Natural and Artificial Systems , pp. 279-300
    • Hart, S.1    Grupen, R.2
  • 13
    • 23144448134 scopus 로고    scopus 로고
    • Novelty and reinforcement learning in the value system of developmental robots
    • eds C. Prince, Y. Demiris, Y. Marom, H. Kozima, and C. Balkenius (Lund: Lund University Cognitive Studies)
    • Huang, X., and Weng, J. (2002). "Novelty and reinforcement learning in the value system of developmental robots," in Proceedings of the Second International Workshop Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems, Vol. 94, eds C. Prince, Y. Demiris, Y. Marom, H. Kozima, and C. Balkenius (Lund: Lund University Cognitive Studies), 47-55.
    • (2002) Proceedings of the Second International Workshop Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems , vol.94 , pp. 47-55
    • Huang, X.1    Weng, J.2
  • 14
    • 0036592029 scopus 로고    scopus 로고
    • Dopamine: generalization and bonuses
    • doi: 10.1016/S0893-6080(02)00048-5
    • Kakade, S., and Dayan, P. (2002). Dopamine: generalization and bonuses. Neural Netw. 15, 549-559. doi: 10.1016/S0893-6080(02)00048-5
    • (2002) Neural Netw. , vol.15 , pp. 549-559
    • Kakade, S.1    Dayan, P.2
  • 15
    • 80055032021 scopus 로고    scopus 로고
    • Skill discovery in continuous reinforcement learning domains using skill chaining
    • eds Y. Bengio, D. Schuurmans, J. Lafferty, C. Williams, and A. Culotta (Vancouver, BC)
    • Konidaris, G., and Barto, A. (2009). "Skill discovery in continuous reinforcement learning domains using skill chaining," in Advances in Neural Information Processing Systems 22 (NIPS '09), eds Y. Bengio, D. Schuurmans, J. Lafferty, C. Williams, and A. Culotta (Vancouver, BC), 1015-1023.
    • (2009) Advances in Neural Information Processing Systems 22 (NIPS '09) , pp. 1015-1023
    • Konidaris, G.1    Barto, A.2
  • 17
    • 0013465187 scopus 로고    scopus 로고
    • Automatic discovery of subgoals in reinforcement learning using diverse density
    • ICML '01, (San Francisco, CA: Morgan Kaufmann Publishers Inc.)
    • McGovern, A., and Barto, A. G. (2001). "Automatic discovery of subgoals in reinforcement learning using diverse density," in Proceedings of the Eighteenth International Conference on Machine Learning, ICML '01, (San Francisco, CA: Morgan Kaufmann Publishers Inc.), 361-368
    • (2001) Proceedings of the Eighteenth International Conference on Machine Learning , pp. 361-368
    • McGovern, A.1    Barto, A.G.2
  • 18
    • 55149090494 scopus 로고    scopus 로고
    • Transfer in variable-reward hierarchical reinforcement learning
    • doi: 10.1007/s10994-008-5061-y
    • Mehta, N., Natarajan, S., Tadepalli, P., and Fern, A. (2008). Transfer in variable-reward hierarchical reinforcement learning. Mach. Learn. 73, 289-312. doi: 10.1007/s10994-008-5061-y
    • (2008) Mach. Learn. , vol.73 , pp. 289-312
    • Mehta, N.1    Natarajan, S.2    Tadepalli, P.3    Fern, A.4
  • 19
    • 84906736869 scopus 로고    scopus 로고
    • Functions and mechanisms of intrinsic motivations: the knowledge vs. competence distinction
    • eds G. Baldassarre, and M. Mirolli (Berlin: Springer-Verlag)
    • Mirolli, M., and Baldassarre, G. (2013). "Functions and mechanisms of intrinsic motivations: the knowledge vs. competence distinction," in Intrinsically Motivated Learning in Natural and Artificial Systems, eds G. Baldassarre, and M. Mirolli (Berlin: Springer-Verlag), 49-72.
    • (2013) Intrinsically Motivated Learning in Natural and Artificial Systems , pp. 49-72
    • Mirolli, M.1    Baldassarre, G.2
  • 20
    • 84872777521 scopus 로고    scopus 로고
    • Phasic dopamine as a prediction error of intrinsic and extrinsic reinforcements driving both action acquisition and reward maximization: a simulated robotic study
    • doi: 10.1016/j.neunet.2012.12.012
    • Mirolli, M., Santucci, V. G., and Baldassarre, G. (2013). Phasic dopamine as a prediction error of intrinsic and extrinsic reinforcements driving both action acquisition and reward maximization: a simulated robotic study. Neural Netw. 39, 40-51. doi: 10.1016/j.neunet.2012.12.012
    • (2013) Neural Netw. , vol.39 , pp. 40-51
    • Mirolli, M.1    Santucci, V.G.2    Baldassarre, G.3
  • 21
    • 78751697580 scopus 로고    scopus 로고
    • Autonomously learning an action hierarchy using a learned qualitative state representation
    • (San Francisco, CA: Morgan Kaufmann Publishers Inc.)
    • Mugan, J., and Kuipers, B. (2009). "Autonomously learning an action hierarchy using a learned qualitative state representation," in Proceedings of the 21st international jont conference on Artifical intelligence, IJCAI'09 (San Francisco, CA: Morgan Kaufmann Publishers Inc.), 1175-1180.
    • (2009) Proceedings of the 21st international jont conference on Artifical intelligence, IJCAI'09 , pp. 1175-1180
    • Mugan, J.1    Kuipers, B.2
  • 22
    • 34047267520 scopus 로고    scopus 로고
    • Intrinsic motivation system for autonomous mental development
    • doi: 10.1109/TEVC.2006.890271
    • Oudeyer, P.-Y., Kaplan, F., and Hafner, V. (2007a). Intrinsic motivation system for autonomous mental development. IEEE Trans. Evol. Comput. 11, 703-713. doi: 10.1109/TEVC.2006.890271
    • (2007) IEEE Trans. Evol. Comput. , vol.11 , pp. 703-713
    • Oudeyer, P.-Y.1    Kaplan, F.2    Hafner, V.3
  • 23
    • 84891105730 scopus 로고    scopus 로고
    • What is intrinsic motivation?. a typology of computational approaches.
    • doi: 10.3389/neuro.12.006.2007
    • Oudeyer, P.-Y., and Kaplan, F. (2007b). What is intrinsic motivation? a typology of computational approaches. Front. Neurorobot. 1:6. doi: 10.3389/neuro.12.006.2007
    • (2007) Front. Neurorobot. , vol.1 , pp. 6
    • Oudeyer, P.-Y.1    Kaplan, F.2
  • 24
    • 0033667258 scopus 로고    scopus 로고
    • Computational approaches to sensorimotor transformations
    • doi: 10.1038/81469
    • Pouget, A., and Snyder, L. H. (2000). Computational approaches to sensorimotor transformations. Nat. Neurosci. 3(Suppl), 1192-1198. doi: 10.1038/81469
    • (2000) Nat. Neurosci. , vol.3 , Issue.SUPPL. , pp. 1192-1198
    • Pouget, A.1    Snyder, L.H.2
  • 25
    • 0002209063 scopus 로고    scopus 로고
    • Intrinsic and extrinsic motivations: classic definitions and new directions
    • doi: 10.1006/ceps.1999.1020
    • Ryan, R. M., and Deci, E. L. (2000). Intrinsic and extrinsic motivations: classic definitions and new directions. Contemp. Educ. Psychol. 25, 54-67. doi: 10.1006/ceps.1999.1020
    • (2000) Contemp. Educ. Psychol. , vol.25 , pp. 54-67
    • Ryan, R.M.1    Deci, E.L.2
  • 26
    • 80055017940 scopus 로고    scopus 로고
    • Biological cumulative learning through intrinsic motivations: a simulated robotic study on the development of visually-guided reaching
    • eds B. Johansson, E. Sahin, and C. Balkenius (Lund: Lund University Cognitive Studies)
    • Santucci, V. G., Baldassarre, G., and Mirolli, M. (2010). "Biological cumulative learning through intrinsic motivations: a simulated robotic study on the development of visually-guided reaching," in Proceedings of the Tenth International Conference on Epigenetic Robotics, eds B. Johansson, E. Sahin, and C. Balkenius (Lund: Lund University Cognitive Studies), 121-127.
    • (2010) Proceedings of the Tenth International Conference on Epigenetic Robotics , pp. 121-127
    • Santucci, V.G.1    Baldassarre, G.2    Mirolli, M.3
  • 28
    • 84904864579 scopus 로고    scopus 로고
    • Cumulative learning through intrinsic reinforcements
    • eds S. Cagnoni, M. Mirolli, and M. Villani (Berlin: Springer-Verlag).
    • Santucci, V. G., Baldassarre, G., and Mirolli, M. (2013a). "Cumulative learning through intrinsic reinforcements," in Evolution, Complexity and Artificial Life eds S. Cagnoni, M. Mirolli, and M. Villani (Berlin: Springer-Verlag).
    • (2013) Evolution, Complexity and Artificial Life
    • Santucci, V.G.1    Baldassarre, G.2    Mirolli, M.3
  • 30
    • 79958838807 scopus 로고    scopus 로고
    • Evolving childhood's length and learning parameters in an intrinsically motivated reinforcement learning robot
    • eds L. Berthouze, G. Dhristiopher, M. Littman, H. Kozima, and C. Balkenius (Lund: Lund University Cognitive Studies)
    • Schembri, M., Mirolli, M., and Baldassarre, G. (2007a). "Evolving childhood's length and learning parameters in an intrinsically motivated reinforcement learning robot," in Proceedings of the Seventh International Conference on Epigenetic Robotics, eds L. Berthouze, G. Dhristiopher, M. Littman, H. Kozima, and C. Balkenius (Lund: Lund University Cognitive Studies), 141-148.
    • (2007) Proceedings of the Seventh International Conference on Epigenetic Robotics , pp. 141-148
    • Schembri, M.1    Mirolli, M.2    Baldassarre, G.3
  • 31
    • 50849094213 scopus 로고    scopus 로고
    • Evolving internal reinforcers for an intrinsically motivated reinforcement-learning robot
    • eds Y. Demiris, D. Mareschal, B. Scassellati, and J. Weng, (London: Imperial College)
    • Schembri, M., Mirolli, M., and Baldassarre, G. (2007b). "Evolving internal reinforcers for an intrinsically motivated reinforcement-learning robot," in Proceedings of the 6th International Conference on Development and Learning, eds Y. Demiris, D. Mareschal, B. Scassellati, and J. Weng, (London: Imperial College), E1-E6.
    • (2007) Proceedings of the 6th International Conference on Development and Learning
    • Schembri, M.1    Mirolli, M.2    Baldassarre, G.3
  • 32
    • 2442467081 scopus 로고
    • A possibility for implementing curiosity and boredom in model-building neural controllers
    • eds J. Meyer, and S. Wilson (Cambridge, MA/London: MIT Press/Bradford Books)
    • Schmidhuber, J. (1991a). "A possibility for implementing curiosity and boredom in model-building neural controllers," in Proceedings of the International Conference on Simulation of Adaptive Behavior: From Animals to Animats, eds J. Meyer, and S. Wilson (Cambridge, MA/London: MIT Press/Bradford Books), 222-227.
    • (1991) Proceedings of the International Conference on Simulation of Adaptive Behavior: From Animals to Animats , pp. 222-227
    • Schmidhuber, J.1
  • 36
    • 0033170372 scopus 로고    scopus 로고
    • Between mdps and semi-mdps: a framework for temporal abstraction in reinforcement learning
    • doi: 10.1016/S0004-3702(99)00052-1
    • Sutton, R., Precup, D., and Singh, S. (1999). Between mdps and semi-mdps: a framework for temporal abstraction in reinforcement learning. Artif. Intell. 112, 181-211. doi: 10.1016/S0004-3702(99)00052-1
    • (1999) Artif. Intell. , vol.112 , pp. 181-211
    • Sutton, R.1    Precup, D.2    Singh, S.3
  • 38
    • 80054969173 scopus 로고    scopus 로고
    • Intrinsically motivated hierarchical skill learning in structured environments
    • doi: 10.1109/TAMD.2010.2050205
    • Vigorito, C., and Barto, A. (2010). Intrinsically motivated hierarchical skill learning in structured environments. IEEE Trans. Auton. Ment. Dev. 2, 132-143. doi: 10.1109/TAMD.2010.2050205
    • (2010) IEEE Trans. Auton. Ment. Dev. , vol.2 , pp. 132-143
    • Vigorito, C.1    Barto, A.2
  • 39
    • 33749411161 scopus 로고
    • Motivation reconsidered: the concept of competence
    • doi: 10.1037/h0040934
    • White, R. (1959). Motivation reconsidered: the concept of competence. Psychol. Rev. 66, 297-333. doi: 10.1037/h0040934
    • (1959) Psychol. Rev. , vol.66 , pp. 297-333
    • White, R.1
  • 40
    • 45249097567 scopus 로고    scopus 로고
    • Striatal activity underlies novelty-based choice in humans
    • doi: 10.1016/j.neuron.2008.04.027
    • Wittmann, B., Daw, N., Seymour, B., and Dolan, R. (2008). Striatal activity underlies novelty-based choice in humans. Neuron 58, 967-973. doi: 10.1016/j.neuron.2008.04.027
    • (2008) Neuron , vol.58 , pp. 967-973
    • Wittmann, B.1    Daw, N.2    Seymour, B.3    Dolan, R.4


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.