{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T14:18:37Z","timestamp":1776781117578,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,6,26]],"date-time":"2021-06-26T00:00:00Z","timestamp":1624665600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NRF- 2019M3E5D2A01066267","award":["NRF- 2019M3E5D2A01066267"],"award-info":[{"award-number":["NRF- 2019M3E5D2A01066267"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,6,26]]},"DOI":"10.1145\/3449639.3459386","type":"proceedings-article","created":{"date-parts":[[2021,6,21]],"date-time":"2021-06-21T17:50:43Z","timestamp":1624297843000},"page":"964-972","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Evolutionary meta reinforcement learning for portfolio optimization"],"prefix":"10.1145","author":[{"given":"Myoung Hoon","family":"Ha","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science and Technology, Daejoen, Korea"}]},{"given":"Seung-geun","family":"Chi","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, Korea"}]},{"given":"Sangyeop","family":"Lee","sequence":"additional","affiliation":[{"name":"Samsung Electronics, Gyeonggi-do, Korea"}]},{"given":"Yujin","family":"Cha","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology, Daejoen, Korea"}]},{"given":"Moon","family":"Byung-Ro","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, Korea"}]}],"member":"320","published-online":{"date-parts":[[2021,6,26]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"M. Al-Shedivat T. Bansal Y. Burda I. Sutskever I. Mordatch and P. Abbeel. 2017. Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments. arXiv:1710.03641 [cs] (Oct. 2017). http:\/\/arxiv.org\/abs\/1710.03641 arXiv: 1710.03641.  M. Al-Shedivat T. Bansal Y. Burda I. Sutskever I. Mordatch and P. Abbeel. 2017. Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments. arXiv:1710.03641 [cs] (Oct. 2017). http:\/\/arxiv.org\/abs\/1710.03641 arXiv: 1710.03641."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1086\/276408"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW.2015.83"},{"key":"e_1_3_2_1_4_1","unstructured":"I. Bello H. Pham Q. V. Le M. Norouzi and S. Bengio. 2017. Neural Combinatorial Optimization with Reinforcement Learning. arXiv:1611.09940 [cs stat] (Jan. 2017). http:\/\/arxiv.org\/abs\/1611.09940 arXiv: 1611.09940.  I. Bello H. Pham Q. V. Le M. Norouzi and S. Bengio. 2017. Neural Combinatorial Optimization with Reinforcement Learning. arXiv:1611.09940 [cs stat] (Jan. 2017). http:\/\/arxiv.org\/abs\/1611.09940 arXiv: 1611.09940."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972771.42"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44565-X_12"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143872"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976602753712972"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3205651.3208249"},{"key":"e_1_3_2_1_10_1","volume-title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. In International Conference on Machine Learning. 1126--1135","author":"Finn C.","unstructured":"C. Finn , P. Abbeel , and S. Levine . 2017 . Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. In International Conference on Machine Learning. 1126--1135 . http:\/\/proceedings.mlr.press\/v70\/finn17a.html C. Finn, P. Abbeel, and S. Levine. 2017. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. In International Conference on Machine Learning. 1126--1135. http:\/\/proceedings.mlr.press\/v70\/finn17a.html"},{"key":"e_1_3_2_1_11_1","unstructured":"J. Foerster N. Nardelli G. Farquhar T. Afouras P. H. S. Torr P. Kohli and S. Whiteson. 2017. Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning. arXiv:1702.08887 [cs] (Feb. 2017). http:\/\/arxiv.org\/abs\/1702.08887 arXiv: 1702.08887.  J. Foerster N. Nardelli G. Farquhar T. Afouras P. H. S. Torr P. Kohli and S. Whiteson. 2017. Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning. arXiv:1702.08887 [cs] (Feb. 2017). http:\/\/arxiv.org\/abs\/1702.08887 arXiv: 1702.08887."},{"key":"e_1_3_2_1_12_1","unstructured":"J. N. Foerster R. Y. Chen M. Al-Shedivat S. Whiteson P. Abbeel and I. Mordatch. 2017. Learning with Opponent-Learning Awareness. arXiv:1709.04326 [cs] (Sept. 2017). http:\/\/arxiv.org\/abs\/1709.04326 arXiv: 1709.04326.  J. N. Foerster R. Y. Chen M. Al-Shedivat S. Whiteson P. Abbeel and I. Mordatch. 2017. Learning with Opponent-Learning Awareness. arXiv:1709.04326 [cs] (Sept. 2017). http:\/\/arxiv.org\/abs\/1709.04326 arXiv: 1709.04326."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-012-5320-9"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1162\/evco.1993.1.3.213"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2908812.2908828"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3071178.3071192"},{"key":"e_1_3_2_1_17_1","unstructured":"T. Haarnoja A. Zhou P. Abbeel and S. Levine. 2018. Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor. arXiv:1801.01290 [cs stat] (Aug. 2018). http:\/\/arxiv.org\/abs\/1801.01290 arXiv: 1801.01290.  T. Haarnoja A. Zhou P. Abbeel and S. Levine. 2018. Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor. arXiv:1801.01290 [cs stat] (Aug. 2018). http:\/\/arxiv.org\/abs\/1801.01290 arXiv: 1801.01290."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139103800"},{"key":"e_1_3_2_1_19_1","unstructured":"S. Levine C. Finn T. Darrell and P. Abbeel. 2015. End-to-End Training of Deep Visuomotor Policies. arXiv:1504.00702 [cs] (April 2015). http:\/\/arxiv.org\/abs\/1504.00702 arXiv: 1504.00702.  S. Levine C. Finn T. Darrell and P. Abbeel. 2015. End-to-End Training of Deep Visuomotor Policies. arXiv:1504.00702 [cs] (April 2015). http:\/\/arxiv.org\/abs\/1504.00702 arXiv: 1504.00702."},{"key":"e_1_3_2_1_20_1","unstructured":"T. P. Lillicrap J. J. Hunt A. Pritzel N. Heess T. Erez Y. Tassa D. Silver andD. Wierstra. 2019. Continuous control with deep reinforcement learning. arXiv:1509.02971 [cs stat] (July 2019). http:\/\/arxiv.org\/abs\/1509.02971 arXiv: 1509.02971 version: 6.  T. P. Lillicrap J. J. Hunt A. Pritzel N. Heess T. Erez Y. Tassa D. Silver andD. Wierstra. 2019. Continuous control with deep reinforcement learning. arXiv:1509.02971 [cs stat] (July 2019). http:\/\/arxiv.org\/abs\/1509.02971 arXiv: 1509.02971 version: 6."},{"key":"e_1_3_2_1_21_1","unstructured":"R. Lowe A. Wu Y. Tamar J. Harb P. Abbeel and I. Mordatch. 2017. Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments. arXiv:1706.02275 [cs] (June 2017). http:\/\/arxiv.org\/abs\/1706.02275 arXiv: 1706.02275.  R. Lowe A. Wu Y. Tamar J. Harb P. Abbeel and I. Mordatch. 2017. Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments. arXiv:1706.02275 [cs] (June 2017). http:\/\/arxiv.org\/abs\/1706.02275 arXiv: 1706.02275."},{"key":"e_1_3_2_1_22_1","unstructured":"V. Mnih K. Kavukcuoglu D. Silver A. Graves I. Antonoglou D. Wierstra and M. Riedmiller. 2013. Playing Atari with Deep Reinforcement Learning. arXiv:1312.5602 [cs] (Dec. 2013). http:\/\/arxiv.org\/abs\/1312.5602 arXiv: 1312.5602.  V. Mnih K. Kavukcuoglu D. Silver A. Graves I. Antonoglou D. Wierstra and M. Riedmiller. 2013. Playing Atari with Deep Reinforcement Learning. arXiv:1312.5602 [cs] (Dec. 2013). http:\/\/arxiv.org\/abs\/1312.5602 arXiv: 1312.5602."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"V. Mnih K. Kavukcuoglu D. Silver A. A Rusu J. Veness M. G Bellemare A. Graves M. Riedmiller A. K Fidjeland G. Ostrovski etal 2015. Human-level control through deep reinforcement learning. Nature 518 7540 (2015) 529.  V. Mnih K. Kavukcuoglu D. Silver A. A Rusu J. Veness M. G Bellemare A. Graves M. Riedmiller A. K Fidjeland G. Ostrovski et al. 2015. Human-level control through deep reinforcement learning. Nature 518 7540 (2015) 529.","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/72.935097"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"J. Moody M. Saffell Y. Liao and L. Wu. 1998. Reinforcement learning for trading systems and portfolios: Immediate vs future rewards. In Decision Technologies for Computational Finance. Springer 129--140.  J. Moody M. Saffell Y. Liao and L. Wu. 1998. Reinforcement learning for trading systems and portfolios: Immediate vs future rewards. In Decision Technologies for Computational Finance. Springer 129--140.","DOI":"10.1007\/978-1-4615-5625-1_10"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1099-131X(1998090)17:5\/6<441::AID-FOR707>3.0.CO;2-#"},{"key":"e_1_3_2_1_27_1","unstructured":"A. Nagabandi I. Clavera S. Liu R. S. Fearing P. Abbeel S. Levine and C. Finn. 2018. Learning to Adapt in Dynamic Real-World Environments Through Meta-Reinforcement Learning. arXiv:1803.11347 [cs stat] (March 2018). http:\/\/arxiv.org\/abs\/1803.11347 arXiv: 1803.11347.  A. Nagabandi I. Clavera S. Liu R. S. Fearing P. Abbeel S. Levine and C. Finn. 2018. Learning to Adapt in Dynamic Real-World Environments Through Meta-Reinforcement Learning. arXiv:1803.11347 [cs stat] (March 2018). http:\/\/arxiv.org\/abs\/1803.11347 arXiv: 1803.11347."},{"key":"e_1_3_2_1_28_1","unstructured":"M. Nazari A. Oroojlooy L. V. Snyder and M. Tak\u00e1c. 2018. Deep Reinforcement Learning for Solving the Vehicle Routing Problem. ArXiv abs\/1802.04240 (2018).  M. Nazari A. Oroojlooy L. V. Snyder and M. Tak\u00e1c. 2018. Deep Reinforcement Learning for Solving the Vehicle Routing Problem. ArXiv abs\/1802.04240 (2018)."},{"key":"e_1_3_2_1_29_1","unstructured":"A. Nichol J. Achiam and J. Schulman. 2018. On First-Order Meta-Learning Algorithms. arXiv:1803.02999 [cs] (March 2018). http:\/\/arxiv.org\/abs\/1803.02999 arXiv: 1803.02999.  A. Nichol J. Achiam and J. Schulman. 2018. On First-Order Meta-Learning Algorithms. arXiv:1803.02999 [cs] (March 2018). http:\/\/arxiv.org\/abs\/1803.02999 arXiv: 1803.02999."},{"key":"e_1_3_2_1_30_1","unstructured":"S. P. M. Choi D.-Y. Yeung and N. Zhang. 1999. Hidden-Mode Markov Decision Processes. (Dec. 1999).  S. P. M. Choi D.-Y. Yeung and N. Zhang. 1999. Hidden-Mode Markov Decision Processes. (Dec. 1999)."},{"key":"e_1_3_2_1_31_1","unstructured":"A. Paszke S. Gross F. Massa A. Lerer J. Bradbury G. Chanan T. Killeen Z. Lin N. Gimelshein L. Antiga A. Desmaison A. Kopf E. Yang Z. DeVito M. Raison A. Tejani S. Chilamkurthy B. Steiner J. Fang L. and S. Chintala. 2019. PyTorch: An Imperative Style High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems 32 H. Wallach H. Larochelle A. Beygelzimer F. d'Alch\u00e9-Buc E. Fox and R. Garnett (Eds.). Curran Associates Inc. 8024--8035. http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf  A. Paszke S. Gross F. Massa A. Lerer J. Bradbury G. Chanan T. Killeen Z. Lin N. Gimelshein L. Antiga A. Desmaison A. Kopf E. Yang Z. DeVito M. Raison A. Tejani S. Chilamkurthy B. Steiner J. Fang L. and S. Chintala. 2019. PyTorch: An Imperative Style High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems 32 H. Wallach H. Larochelle A. Beygelzimer F. d'Alch\u00e9-Buc E. Fox and R. Garnett (Eds.). Curran Associates Inc. 8024--8035. http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"key":"e_1_3_2_1_32_1","volume-title":"Simulationsmethoden in der Medizin und Biologie (Medizinische Informatik und Statistik)","author":"Rechenberg I.","unstructured":"I. Rechenberg . 1978. Evolutionsstrategien . In Simulationsmethoden in der Medizin und Biologie (Medizinische Informatik und Statistik) , Berthold Schneider and Ulrich Ranft (Eds.). Springer Berlin Heidelberg , 83--114. I. Rechenberg. 1978. Evolutionsstrategien. In Simulationsmethoden in der Medizin und Biologie (Medizinische Informatik und Statistik), Berthold Schneider and Ulrich Ranft (Eds.). Springer Berlin Heidelberg, 83--114."},{"key":"e_1_3_2_1_33_1","unstructured":"T. Salimans J. Ho X. Chen S. Sidor and I. Sutskever. 2017. Evolution Strategies as a Scalable Alternative to Reinforcement Learning. arXiv:1703.03864 [cs stat] (March 2017). http:\/\/arxiv.org\/abs\/1703.03864 arXiv: 1703.03864.  T. Salimans J. Ho X. Chen S. Sidor and I. Sutskever. 2017. Evolution Strategies as a Scalable Alternative to Reinforcement Learning. arXiv:1703.03864 [cs stat] (March 2017). http:\/\/arxiv.org\/abs\/1703.03864 arXiv: 1703.03864."},{"key":"e_1_3_2_1_34_1","volume-title":"Evolutionary Principles in Self-Referential Learning. On Learning now to Learn: The Meta-Meta-Meta...-Hook. Diploma Thesis","author":"Schmidhuber J.","unstructured":"J. Schmidhuber . 1987. Evolutionary Principles in Self-Referential Learning. On Learning now to Learn: The Meta-Meta-Meta...-Hook. Diploma Thesis . Technische Universitat Munchen , Germany. http:\/\/www.idsia.ch\/~juergen\/diploma.html J. Schmidhuber. 1987. Evolutionary Principles in Self-Referential Learning. On Learning now to Learn: The Meta-Meta-Meta...-Hook. Diploma Thesis. Technische Universitat Munchen, Germany. http:\/\/www.idsia.ch\/~juergen\/diploma.html"},{"key":"e_1_3_2_1_35_1","unstructured":"J. Schulman F. Wolski P. Dhariwal A. Radford and O. Klimov. 2017. Proximal Policy Optimization Algorithms. arXiv:1707.06347 [cs] (July 2017). http:\/\/arxiv.org\/abs\/1707.06347 arXiv: 1707.06347.  J. Schulman F. Wolski P. Dhariwal A. Radford and O. Klimov. 2017. Proximal Policy Optimization Algorithms. arXiv:1707.06347 [cs] (July 2017). http:\/\/arxiv.org\/abs\/1707.06347 arXiv: 1707.06347."},{"key":"e_1_3_2_1_36_1","volume-title":"Numerische Optimierung von Computer - Modellen. (Jan","author":"Schwefel H.-P.","year":"1974","unstructured":"H.-P. Schwefel . 1974. Numerische Optimierung von Computer - Modellen. (Jan . 1974 ). H.-P. Schwefel. 1974. Numerische Optimierung von Computer - Modellen. (Jan. 1974)."},{"key":"e_1_3_2_1_37_1","volume-title":"J. Schrittwieser, I. Antonoglou, V. Panneershelvam, M. Lanctot, et al.","author":"Silver D.","year":"2016","unstructured":"D. Silver , A. Huang , C. J. Maddison , A. Guez , L. Sifre , G. Van Den Driessche , J. Schrittwieser, I. Antonoglou, V. Panneershelvam, M. Lanctot, et al. 2016 . Mastering the game of Go with deep neural networks and tree search. nature 529, 7587 (2016), 484. D. Silver, A. Huang, C. J. Maddison, A. Guez, L. Sifre, G. Van Den Driessche, J. Schrittwieser, I. Antonoglou, V. Panneershelvam, M. Lanctot, et al. 2016. Mastering the game of Go with deep neural networks and tree search. nature 529, 7587 (2016), 484."},{"key":"e_1_3_2_1_38_1","volume-title":"Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning. arXiv:1712.06567 [cs] (Dec.","author":"Such F. P.","year":"2017","unstructured":"F. P. Such , V. Madhavan , E. Conti , J. Lehman , K. O. Stanley , and J. Clune . 2017 . Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning. arXiv:1712.06567 [cs] (Dec. 2017). http:\/\/arxiv.org\/abs\/1712.06567 arXiv: 1712.06567. F. P. Such, V. Madhavan, E. Conti, J. Lehman, K. O. Stanley, and J. Clune. 2017. Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning. arXiv:1712.06567 [cs] (Dec. 2017). http:\/\/arxiv.org\/abs\/1712.06567 arXiv: 1712.06567."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZ-IEEE.2014.6891757"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-58484-6_245"},{"key":"e_1_3_2_1_41_1","unstructured":"B. Zoph and Q. V. Le. 2016. Neural Architecture Search with Reinforcement Learning. arXiv:1611.01578 [cs] (Nov. 2016). http:\/\/arxiv.org\/abs\/1611.01578 arXiv: 1611.01578.  B. Zoph and Q. V. Le. 2016. Neural Architecture Search with Reinforcement Learning. arXiv:1611.01578 [cs] (Nov. 2016). http:\/\/arxiv.org\/abs\/1611.01578 arXiv: 1611.01578."}],"event":{"name":"GECCO '21: Genetic and Evolutionary Computation Conference","location":"Lille France","acronym":"GECCO '21","sponsor":["SIGEVO ACM Special Interest Group on Genetic and Evolutionary Computation"]},"container-title":["Proceedings of the Genetic and Evolutionary Computation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3449639.3459386","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3449639.3459386","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:28:09Z","timestamp":1750195689000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3449639.3459386"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,26]]},"references-count":41,"alternative-id":["10.1145\/3449639.3459386","10.1145\/3449639"],"URL":"https:\/\/doi.org\/10.1145\/3449639.3459386","relation":{},"subject":[],"published":{"date-parts":[[2021,6,26]]},"assertion":[{"value":"2021-06-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}