{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:37:53Z","timestamp":1742913473136,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789811681127"},{"type":"electronic","value":"9789811681134"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-981-16-8113-4_1","type":"book-chapter","created":{"date-parts":[[2022,2,11]],"date-time":"2022-02-11T05:06:04Z","timestamp":1644555964000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Finding Simple Solutions to Multi-Task Visual Reinforcement Learning Problems with Tangled Program Graphs"],"prefix":"10.1007","author":[{"given":"Caleidgh","family":"Bayer","sequence":"first","affiliation":[]},{"given":"Ryan","family":"Amaral","sequence":"additional","affiliation":[]},{"given":"Robert J.","family":"Smith","sequence":"additional","affiliation":[]},{"given":"Alexandru","family":"Ianta","sequence":"additional","affiliation":[]},{"given":"Malcolm I.","family":"Heywood","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,2,11]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","first-page":"1404","DOI":"10.1126\/science.1082240","volume":"300","author":"I Bjedov","year":"2003","unstructured":"Bjedov, I., Tenaillon, O., Gerard, B., Souza, V., Denamur, E., Radman, M., Taddei, F., Matic, I.: Stress-induced mutagenesis in bacteria. Science 300, 1404\u20131409 (2003)","journal-title":"Science"},{"key":"1_CR2","unstructured":"Brameier, M., Banzhaf, W.: Linear Genetic Programming. Springer (2007)"},{"key":"1_CR3","unstructured":"Branke, J.: Evolutionary approaches to dynamic environments\u2014a survey. In: GECCO Workshop on Dynamic Optimization Problems, pp. 134\u2013137 (1999)"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Cobb, H.G.: An investigation into the use of hypermutation as an adaptive operating in genetic algorithms having continuous, time-dependent non-stationary environments. Technical Report TR AIC-90-001, Naval research Laboratory (1990)","DOI":"10.21236\/ADA229159"},{"key":"1_CR5","first-page":"1","volume":"7","author":"J Demsar","year":"2006","unstructured":"Demsar, J.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7, 1\u201330 (2006)","journal-title":"J. Mach. Learn. Res."},{"key":"1_CR6","unstructured":"Ghosh, A., Tstutsui, S., Tanaka, H.: Function optimization in non-stationary environment using steady state genetic algorithms with aging of individuals. In: IEEE Congress on Evolutionary Computation, pp. 666\u2013671 (1998)"},{"key":"1_CR7","unstructured":"Grefenstette, J.J.: Genetic algorithms for changing environments. In: PPSN, pp. 137\u2013144 (1992)"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Hwangbo, J., Lee, J., Dosovitskiy, A., Bellicoso, D., Tsounis, V., Koltun, V., Hutter, M.: Learning agile and dynamic motor skills for legged robots. CoRR (2019). arXiv:abs\/1901.08652","DOI":"10.1126\/scirobotics.aau5872"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Ianta, A., Amaral, R., Bayer, C., Smith, R.J., Heywood, M.I.: On the impact of tangled program graph marking schemes under the atari reinforcement learning benchmark. In: Proceedings of the ACM Genetic and Evolutionary Computation Conference, p. to appear (2021)","DOI":"10.1145\/3449639.3459348"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Jaderberg, M., Czarnecki, W.M., Dunning, I., Marris, L., Lever, G., Casta\u00f1eda, A.G., Beattie, C., Rabinowitz, N.C., Morcos, A.S., Ruderman, A., Sonnerat, N., Green, T., Deason, L., Leibo, J.Z., Silver, D., Hassabis, D., Kavukcuoglu, K., Graepel, T.: Human-level performance in 3D multiplayer games with population-based reinforcement learning. Science 364, 859\u2013865 (2019)","DOI":"10.1126\/science.aau6249"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Kelly, S., Heywood, M.I.: Emergent tangled graph representations for atari game playing agents. In: European Conference on Genetic Programming, LNCS, vol. 10196, pp. 64\u201379 (2017)","DOI":"10.1007\/978-3-319-55696-3_5"},{"issue":"3","key":"1_CR12","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1162\/evco_a_00232","volume":"26","author":"S Kelly","year":"2018","unstructured":"Kelly, S., Heywood, M.I.: Emergent solutions to high-dimensional multitask reinforcement learning. Evol. Comput. 26(3), 347\u2013380 (2018)","journal-title":"Evol. Comput."},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Kelly, S., Newsted, J., Banzhaf, W., Gondro, C.: A modular memory framework for time series prediction. In: Proceedings of the ACM Genetic and Evolutionary Computation Conference, pp. 949\u2013957 (2020)","DOI":"10.1145\/3377930.3390216"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Kelly, S., Smith, R.J., Heywood, M.I.: Emergent policy discovery for visual reinforcement learning through tangled program graphs: a tutorial. In: Banzhaf, W., Spector, L., Sheneman L (eds.) Genetic Programming Theory and Practice XVI, Genetic and Evolutionary Computation, pp. 37\u201357 (2018)","DOI":"10.1007\/978-3-030-04735-1_3"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Kelly, S., Smith, R.J., Heywood, M.I., Banzhaf, W.: Emergent tangled program graphs in partially observable recursive forecasting and ViZDoom navigation tasks. ACM Trans. Evol. Learn. Optim. 1 (2021)","DOI":"10.1145\/3468857"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Kempka, M., Wydmuch, M., Runc, G., Toczek, J., Jaskowski, W.: ViZDoom: A Doom-based AI research platform for visual reinforcement learning. In: IEEE Conference on Computational Intelligence and Games, pp. 1\u20138 (2016)","DOI":"10.1109\/CIG.2016.7860433"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Koza, J.R.: Genetic Programming\u2014On the Programming of Computers by Means of Natural Selection. MIT Press, Complex Adaptive Systems (1993)","DOI":"10.1007\/BF00175355"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Moriarty, D.E., Schultz, A.C., Grefenstette, J.J.: Evolutionary algorithms for reinforcement learning. J. Artif. Intell. Res. 11, 199\u2013229 (1999)","DOI":"10.1613\/jair.613"},{"issue":"11","key":"1_CR19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1371\/journal.pcbi.1000206","volume":"4","author":"M Parter","year":"2008","unstructured":"Parter, M., Kashtan, N., Alon, U.: Facilitated variation: how evolution learns from past environments to generalize to new environments. PLOS Comput. Biol. 4(11), 1\u201315 (2008)","journal-title":"PLOS Comput. Biol."},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Smith, R.J., Heywood, M.I.: Scaling tangled program graphs to visual reinforcement learning in ViZDoom. In: European Conference on Genetic Programming, Lecture LNCS, vol. 10781, pp. 135\u2013150 (2018)","DOI":"10.1007\/978-3-319-77553-1_9"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Smith, R.J., Heywood, M.I.: Evolving Dota 2 shadow fiend bots using genetic programming with external memory. In: Proceedings of the ACM Genetic and Evolutionary Computation Conference, pp. 179\u2013187 (2019)","DOI":"10.1145\/3321707.3321866"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Smith, R.J., Heywood, M.I.: A model of external memory for navigation in partially observable visual reinforcement learning tasks. In: European Conference on Genetic Programming, LNCS, vol. 11451, pp. 162\u2013177 (2019)","DOI":"10.1007\/978-3-030-16670-0_11"},{"issue":"4\u20135","key":"1_CR23","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1177\/0278364918770733","volume":"37","author":"N S\u00fcnderhauf","year":"2018","unstructured":"S\u00fcnderhauf, N., Brock, O., Scheirer, W.J., Hadsell, R., Fox, D., Leitner, J., Upcroft, B., Abbeel, P., Burgard, W., Milford, M., Corke, P.: The limits and potentials of deep learning for robotics. Int. J. Robot. Res. 37(4\u20135), 405\u2013420 (2018)","journal-title":"Int. J. Robot. Res."},{"key":"1_CR24","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT (2018)"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Teng, G., Popavasiliou, F.N.: Immunoglobulin somatic hypermutation. Annu. Rev. Genet. 41, 107\u2013120 (2007)","DOI":"10.1146\/annurev.genet.41.110306.130340"}],"container-title":["Genetic and Evolutionary Computation","Genetic Programming Theory and Practice XVIII"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-16-8113-4_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,3]],"date-time":"2022-05-03T16:14:33Z","timestamp":1651594473000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-16-8113-4_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9789811681127","9789811681134"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-16-8113-4_1","relation":{},"ISSN":["1932-0167","1932-0175"],"issn-type":[{"type":"print","value":"1932-0167"},{"type":"electronic","value":"1932-0175"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 February 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}