{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T07:16:28Z","timestamp":1726038988016},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030244040"},{"type":"electronic","value":"9783030244057"}],"license":[{"start":{"date-parts":[[2019,7,31]],"date-time":"2019-07-31T00:00:00Z","timestamp":1564531200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-24405-7_2","type":"book-chapter","created":{"date-parts":[[2019,7,30]],"date-time":"2019-07-30T07:03:37Z","timestamp":1564470217000},"page":"19-32","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-task Deep Reinforcement Learning with Evolutionary Algorithm and Policy Gradients Method in 3D Control Tasks"],"prefix":"10.1007","author":[{"given":"Shota","family":"Imai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuichi","family":"Sei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasuyuki","family":"Tahara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryohei","family":"Orihara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akihiko","family":"Ohsuga","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,7,31]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Andrychowicz, M., Baker, B., Chociej, M., J\u00f3zefowicz, R., McGrew, B., Pachocki, J.W., Petron, A., Plappert, M., Powell, G., Ray, A., Schneider, J., Sidor, S., Tobin, J., Welinder, P., Weng, L., Zaremba, W.: Learning dexterous in-hand manipulation. CoRR arXiv:1808.00177 (2018)","DOI":"10.1177\/0278364919887447"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. CoRR arXiv:1207.4708 (2012)","DOI":"10.1613\/jair.3912"},{"key":"2_CR3","unstructured":"Brockman, G., Cheung, V., Pettersson, L., Schneider, J., Schulman, J., Tang, J., Zaremba, W.: OpenAI gym. CoRR arXiv:1606.01540 (2016)"},{"key":"2_CR4","unstructured":"Coumans, E., Bai, Y.: Pybullet, a python module for physics simulation for games, robotics and machine learning (2016\u20132019). http:\/\/pybullet.org"},{"key":"2_CR5","unstructured":"Duan, Y., Chen, X., Houthooft, R., Schulman, J., Abbeel, P.: Benchmarking deep reinforcement learning for continuous control. CoRR arXiv:1604.06778 (2016)"},{"key":"2_CR6","unstructured":"Espeholt, L., Soyer, H., Munos, R., Simonyan, K., Mnih, V., Ward, T., Doron, Y., Firoiu, V., Harley, T., Dunning, I., Legg, S., Kavukcuoglu, K.: IMPALA: scalable distributed deep-RL with importance weighted actor-learner architectures. CoRR arXiv:1802.01561 (2018)"},{"key":"2_CR7","unstructured":"Fernando, C., Banarse, D., Blundell, C., Zwols, Y., Ha, D., Rusu, A.A., Pritzel, A., Wierstra, D.: Pathnet: evolution channels gradient descent in super neural networks. CoRR arXiv:1701.08734 (2017)"},{"key":"2_CR8","unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the 34th International Conference on Machine Learning, Proceedings of Machine Learning Research, vol.\u00a070, pp. 1126\u20131135. PMLR, International Convention Centre, Sydney, Australia (2017). http:\/\/proceedings.mlr.press\/v70\/finn17a.html"},{"issue":"1","key":"2_CR9","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1007\/s12065-007-0002-4","volume":"1","author":"Dario Floreano","year":"2008","unstructured":"Floreano, D., Durr, P., Mattiussi, C.: Neuroevolution: from architectures to learning (2008)","journal-title":"Evolutionary Intelligence"},{"key":"2_CR10","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/S1364-6613(99)01294-2","volume":"3","author":"RM French","year":"1999","unstructured":"French, R.M.: Catastrophic forgetting in connectionist networks. Trends Cogn. Sci. 3, 128\u2013135 (1999)","journal-title":"Trends Cogn. Sci."},{"key":"2_CR11","unstructured":"Fujimoto, S., van Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. CoRR arXiv:1802.09477 (2018)"},{"key":"2_CR12","unstructured":"Hasselt, H.V.: In: Lafferty, J.D., Williams, C.K.I., Shawe-Taylor, J., Zemel, R.S., Culotta, A. (eds.) Advances in Neural Information Processing Systems, vol. 23, pp. 2613\u20132621. Curran Associates, Inc. (2010). http:\/\/papers.nips.cc\/paper\/3964-double-q-learning.pdf"},{"key":"2_CR13","unstructured":"Hasselt, H.V., Guez, A., Silver, D.: Deep reinforcement learning with double Q-learning. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, AAAI\u201916, pp. 2094\u20132100. AAAI Press (2016). http:\/\/dl.acm.org\/citation.cfm?id=3016100.3016191"},{"key":"2_CR14","unstructured":"Hausknecht, M., Lehman, J., Miikkulainen, R., Stone, P.: A neuroevolution approach to general atari game playing. IEEE Trans. Comput. Intell. AI Games (2013). http:\/\/nn.cs.utexas.edu\/?hausknecht:tciaig14"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Henderson, P., Islam, R., Bachman, P., Pineau, J., Precup, D., Meger, D.: Deep reinforcement learning that matters. CoRR arXiv:1709.06560 (2017)","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"2_CR16","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS Deep Learning and Representation Learning Workshop. arXiv:1503.02531 (2015)"},{"issue":"5","key":"2_CR17","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","volume":"2","author":"Kurt Hornik","year":"1989","unstructured":"Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2(5), 359\u2013366 (1989). https:\/\/doi.org\/10.1016\/0893-6080(89)90020-8","journal-title":"Neural Networks"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"James, S., Wohlhart, P., Kalakrishnan, M., Kalashnikov, D., Irpan, A., Ibarz, J., Levine, S., Hadsell, R., Bousmalis, K.: Sim-to-real via sim-to-sim: data-efficient robotic grasping via randomized-to-canonical adaptation networks. CoRR arXiv:1812.07252 (2018)","DOI":"10.1109\/CVPR.2019.01291"},{"key":"2_CR19","unstructured":"Kapturowski, S., Ostrovski, G., Dabney, W., Quan, J., Munos, R.: Recurrent experience replay in distributed reinforcement learning. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=r1lyTjAqYX"},{"key":"2_CR20","unstructured":"Khadka, S., Tumer, K.: Evolution-guided policy gradient in reinforcement learning. In: Bengio, S., Wallach, H., Larochelle,H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 31, pp. 1196\u20131208. Curran Associates, Inc. (2018). http:\/\/papers.nips.cc\/paper\/7395-evolution-guided-policy-gradient-in-reinforcement-learning.pdf"},{"key":"2_CR21","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR arXiv:1412.6980 (2014)"},{"key":"2_CR22","unstructured":"Kolen, J.F., Pollack, J.B.: Back propagation is sensitive to initial conditions. In: Proceedings of the 1990 Conference on Advances in Neural Information Processing Systems 3, NIPS-3, pp. 860\u2013867. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA (1990). http:\/\/dl.acm.org\/citation.cfm?id=118850.119960"},{"key":"2_CR23","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25, pp. 1097\u20131105. Curran Associates, Inc. (2012). http:\/\/papers.nips.cc\/paper\/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf"},{"key":"2_CR24","unstructured":"Levine, S., Finn, C., Darrell, T., Abbeel, P.: End-to-end training of deep visuomotor policies. J. Mach. Learn. Res. 17(39), 1\u201340 (2016). http:\/\/jmlr.org\/papers\/v17\/15-522.html"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Levine, S., Pastor, P., Krizhevsky, A., Quillen, D.: Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection. CoRR arXiv:1603.02199 (2016)","DOI":"10.1007\/978-3-319-50115-4_16"},{"key":"2_CR26","unstructured":"Lillicrap, T.P., Hunt, J.J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., Wierstra, D.: Continuous control with deep reinforcement learning. CoRR arXiv:1509.02971 (2015)"},{"key":"2_CR27","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing atari with deep reinforcement learning. In: NIPS Deep Learning Workshop (2013)"},{"issue":"7540","key":"2_CR28","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"Volodymyr Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., Hassabis, D.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015). https:\/\/doi.org\/10.1038\/nature14236","journal-title":"Nature"},{"issue":"1","key":"2_CR29","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s10479-005-5724-z","volume":"134","author":"Pieter-Tjerk de Boer","year":"2005","unstructured":"Pieter-Tjerk, Kroese, D.P., Mannor, S., Rubinstein, R.Y.: A tutorial on the cross-entropy method. Ann. Oper. Res. 134(1), 19\u201367 (2005). https:\/\/doi.org\/10.1007\/s10479-005-5724-z","journal-title":"Annals of Operations Research"},{"key":"2_CR30","unstructured":"Pourchot, Sigaud: CEM-RL: combining evolutionary and gradient-based methods for policy search. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=BkeU5j0ctQ"},{"key":"2_CR31","unstructured":"Salimans, T., Ho, J., Chen, X., Sutskever, I.: Evolution strategies as a scalable alternative to reinforcement learning. CoRR arXiv:1703.03864 (2017)"},{"key":"2_CR32","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. CoRR arXiv:1511.05952 (2016)"},{"issue":"7587","key":"2_CR33","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C.J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., Dieleman, S., Grewe, D., Nham, J., Kalchbrenner, N., Sutskever, I., Lillicrap, T., Leach, M., Kavukcuoglu, K., Graepel, T., Hassabis, D.: Mastering the game of Go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016). https:\/\/doi.org\/10.1038\/nature16961","journal-title":"Nature"},{"key":"2_CR34","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: Xing, E.P., Jebara, T. (eds.) Proceedings of the 31st International Conference on Machine Learning, Proceedings of Machine Learning Research, vol.\u00a032, pp. 387\u2013395. PMLR, Bejing, China (2014). http:\/\/proceedings.mlr.press\/v32\/silver14.html"},{"issue":"2","key":"2_CR35","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1162\/106365602320169811","volume":"10","author":"Kenneth O. Stanley","year":"2002","unstructured":"Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10(2), 99\u2013127 (2002). https:\/\/doi.org\/10.1162\/106365602320169811","journal-title":"Evolutionary Computation"},{"key":"2_CR36","volume-title":"Introduction to Reinforcement Learning","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning, 1st edn. MIT Press, Cambridge, MA, USA (1998)","edition":"1"},{"key":"2_CR37","unstructured":"Teh, Y., Bapst, V., Czarnecki, W.M., Quan, J., Kirkpatrick, J., Hadsell, R., Heess, N., Pascanu, R.: Distral: robust multitask reinforcement learning. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 30, pp. 4496\u20134506. Curran Associates, Inc. (2017). http:\/\/papers.nips.cc\/paper\/7036-distral-robust-multitask-reinforcement-learning.pdf"},{"issue":"3-4","key":"2_CR38","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"Christopher J. C. H. Watkins","year":"1992","unstructured":"Watkins, C.J.C.H., Dayan, P.: Q-learning. Mach. Learn. 8(3), 279\u2013292 (1992). https:\/\/doi.org\/10.1007\/BF00992698","journal-title":"Machine Learning"}],"container-title":["Studies in Computational Intelligence","Big Data, Cloud Computing, and Data Science Engineering"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-24405-7_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,24]],"date-time":"2022-09-24T17:10:54Z","timestamp":1664039454000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-24405-7_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,31]]},"ISBN":["9783030244040","9783030244057"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-24405-7_2","relation":{},"ISSN":["1860-949X","1860-9503"],"issn-type":[{"type":"print","value":"1860-949X"},{"type":"electronic","value":"1860-9503"}],"subject":[],"published":{"date-parts":[[2019,7,31]]},"assertion":[{"value":"31 July 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BCD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3rd IEEE\/ACIS International Conference on Big Data, Cloud Computing, and Data Science Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Honolulu , HI","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 May 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 May 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bcd2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.acisinternational.org\/bcd2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}