메뉴 건너뛰기




Volumn 33, Issue 4, 2012, Pages 361-379

Reinforcement learning to adjust parametrized motor primitives to new situations

Author keywords

Meta parameters; Motor primitives; Policy learning; Reinforcement learning; Skill learning

Indexed keywords

CURRENT SITUATION; GLOBAL PARAMETERS; HITTING MOVEMENTS; META-PARAMETERS; MOTOR PRIMITIVES; PHYSICAL ROBOTS; ROBOT TASKS; SKILL LEARNING; TABLE-TENNIS;

EID: 84868358933     PISSN: 09295593     EISSN: None     Source Type: Journal    
DOI: 10.1007/s10514-012-9290-3     Document Type: Article
Times cited : (166)

References (44)
  • 1
    • 0141988716 scopus 로고    scopus 로고
    • Recent advances in hierarchical reinforcement learning
    • Barto, A., & Mahadevan, S. (2003). Recent advances in hierarchical reinforcement learning. Discrete Event Dynamic Systems, 13(4), 341-379.
    • (2003) Discrete Event Dynamic Systems , vol.13 , Issue.4 , pp. 341-379
    • Barto, A.1    Mahadevan, S.2
  • 2
    • 33846239996 scopus 로고    scopus 로고
    • Computational principles of sensorimotor control that minimize uncertainty and variability
    • DOI 10.1113/jphysiol.2006.120121
    • Bays, P., & Wolpert, D. (2007). Computational principles of sensorimotor control that minimise uncertainty and variability. Journal of Physiology, 578, 387-396. (Pubitemid 46092204)
    • (2007) Journal of Physiology , vol.578 , Issue.2 , pp. 387-396
    • Bays, P.M.1    Wolpert, D.M.2
  • 5
    • 0031189914 scopus 로고    scopus 로고
    • Multitask learning
    • Caruana, R. (1997). Multitask learning. Machine Learning, 28, 41-75. (Pubitemid 127507169)
    • (1997) Machine Learning , vol.28 , Issue.1 , pp. 41-75
    • Caruana, R.1
  • 7
    • 0346982426 scopus 로고    scopus 로고
    • Using expectation-maximization for reinforcement learning
    • Dayan, P., & Hinton, G. E. (1997). Using expectation-maximization for reinforcement learning. Neural Computation, 9(2), 271-278. (Pubitemid 127635391)
    • (1997) Neural Computation , vol.9 , Issue.2 , pp. 271-278
    • Dayan, P.1    Hinton, G.E.2
  • 8
    • 0036592023 scopus 로고    scopus 로고
    • Metalearning and neuromodulation
    • DOI 10.1016/S0893-6080(02)00044-8, PII S0893608002000448
    • Doya, K. (2002). Metalearning and neuromodulation. Neural Networks, 15(4-6), 495-506. (Pubitemid 34947460)
    • (2002) Neural Networks , vol.15 , Issue.4-6 , pp. 495-506
    • Doya, K.1
  • 14
    • 71149100038 scopus 로고    scopus 로고
    • Trajectory prediction: Learning to map situations to robot trajectories
    • Jetchev, N., & Toussaint, M. (2009). Trajectory prediction: learning to map situations to robot trajectories. In Proc. int. conf. machine learning (p. 57).
    • (2009) Proc. Int. Conf. Machine Learning , pp. 57
    • Jetchev, N.1    Toussaint, M.2
  • 16
    • 78049390740 scopus 로고    scopus 로고
    • Policy search for motor primitives in robotics
    • Kober, J., & Peters, J. (2011b). Policy search for motor primitives in robotics. Machine Learning, 84(1-2), 171-203.
    • (2011) Machine Learning , vol.84 , Issue.1-2 , pp. 171-203
    • Kober, J.1    Peters, J.2
  • 23
    • 84868354885 scopus 로고    scopus 로고
    • Masters Games Ltd (2010). The rules of darts. http://www.mastersgames. com/rules/darts-rules.htm.
    • (2010) The Rules of Darts
  • 24
    • 0013465187 scopus 로고    scopus 로고
    • Automatic discovery of subgoals in reinforcement learning using diverse density
    • McGovern, A., & Barto, A. G. (2001). Automatic discovery of subgoals in reinforcement learning using diverse density. In Proc. int. conf. machine learning (pp. 361-368).
    • (2001) Proc. Int. Conf. Machine Learning , pp. 361-368
    • McGovern, A.1    Barto, A.G.2
  • 27
    • 80054858850 scopus 로고    scopus 로고
    • A biomimetic approach to robot table tennis
    • Mülling, K., Kober, J., & Peters, J. (2011). A biomimetic approach to robot table tennis. Adaptive Behavior, 9(5), 359-376.
    • (2011) Adaptive Behavior , vol.9 , Issue.5 , pp. 359-376
    • Mülling, K.1    Kober, J.2    Peters, J.3
  • 29
    • 63549125238 scopus 로고    scopus 로고
    • Movement reproduction and obstacle avoidance with dynamic movement primitives and potential fields
    • Park, D. H., Hoffmann, H., Pastor, P., & Schaal, S. (2008). Movement reproduction and obstacle avoidance with dynamic movement primitives and potential fields. In Proc. IEEE-RAS int. conf. humanoid robots (pp. 91-98).
    • (2008) Proc IEEE-RAS Int. Conf. Humanoid Robots , pp. 91-98
    • Park, D.H.1    Hoffmann, H.2    Pastor, P.3    Schaal, S.4
  • 31
    • 38649095925 scopus 로고    scopus 로고
    • Learning to control in operational space
    • DOI 10.1177/0278364907087548
    • Peters, J., & Schaal, S. (2008a). Learning to control in operational space. The International Journal of Robotics Research, 27(2), 197-212. (Pubitemid 351169714)
    • (2008) International Journal of Robotics Research , vol.27 , Issue.2 , pp. 197-212
    • Peters, J.1    Schaal, S.2
  • 32
    • 44949241322 scopus 로고    scopus 로고
    • Reinforcement learning of motor skills with policy gradients
    • Peters, J., & Schaal, S. (2008b). Reinforcement learning of motor skills with policy gradients. Neural Networks, 21(4), 682-697.
    • (2008) Neural Networks , vol.21 , Issue.4 , pp. 682-697
    • Peters, J.1    Schaal, S.2
  • 36
    • 34848832311 scopus 로고    scopus 로고
    • Dynamics systems vs. optimal control - A unifying view
    • DOI 10.1016/S0079-6123(06)65027-9, PII S0079612306650279, Computational Neuroscience: Theoretical Insights into Brain Function
    • Schaal, S., Mohajerian, P., & Ijspeert, A. J. (2007). Dynamics systems vs. optimal control - a unifying view. Progress in Brain Research, 165(1), 425-445. (Pubitemid 47513886)
    • (2007) Progress in Brain Research , vol.165 , pp. 425-445
    • Schaal, S.1    Mohajerian, P.2    Ijspeert, A.3
  • 40
    • 77957706006 scopus 로고    scopus 로고
    • Ask-specific generalization of discrete and periodic dynamic movement primitives
    • Ude, A., Gams, A., Asfour, T., & Morimoto, J. (2010). Task-specific generalization of discrete and periodic dynamic movement primitives. IEEE Transactions on Robotics, 26(5), 800-815.
    • (2010) IEEE Transactions on Robotics , vol.26 , Issue.5 , pp. 800-815
    • Ude, A.1    Gams, A.2    Asfour, T.3    Morimoto, J.4
  • 43
    • 0000337576 scopus 로고
    • Simple statistical gradient-following algorithms for connectionist reinforcement learning
    • Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8, 229-256.
    • (1992) Machine Learning , vol.8 , pp. 229-256
    • Williams, R.J.1


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.