{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T02:45:08Z","timestamp":1743043508466,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030581145"},{"type":"electronic","value":"9783030581152"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","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\/978-3-030-58115-2_35","type":"book-chapter","created":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T22:02:51Z","timestamp":1598997771000},"page":"500-514","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Fitness Landscape Features and Reward Shaping in Reinforcement Learning Policy Spaces"],"prefix":"10.1007","author":[{"given":"Nathaniel","family":"du Preez-Wilkinson","sequence":"first","affiliation":[]},{"given":"Marcus","family":"Gallagher","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,9,2]]},"reference":[{"key":"35_CR1","unstructured":"Ahmed, Z., Le Roux, N., Norouzi, M., Schuurmans, D.: Understanding the impact of entropy on policy optimization. In: Proceedings of the 36th International Conference on Machine Learning (2019)"},{"key":"35_CR2","unstructured":"Chentanez, N., Barto, A.G., Singh, S.P.: Intrinsically motivated reinforcement learning. In: Advances in Neural Information Processing Systems 17, pp. 1281\u20131288. MIT Press (2005)"},{"key":"35_CR3","doi-asserted-by":"crossref","unstructured":"Chrabaszcz, P., Loshchilov, I., Hutter, F.: Back to basics: benchmarking canonical evolution strategies for playing atari. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence, pp. 1419\u20131426. AAAI Press (2018)","DOI":"10.24963\/ijcai.2018\/197"},{"key":"35_CR4","unstructured":"Dosovitskiy, A., Koltun, V.: Learning to act by predicting the future. arXiv preprint \narXiv:1611.01779\n\n (2016)"},{"key":"35_CR5","first-page":"243","volume":"3","author":"J Horn","year":"1995","unstructured":"Horn, J., Goldberg, D.E.: Genetic algorithm difficulty and the modality of fitness landscapes. Found. Genetic Algorithms 3, 243\u2013269 (1995)","journal-title":"Found. Genetic Algorithms"},{"key":"35_CR6","unstructured":"Ilyas, A., et al.: Are deep policy gradient algorithms truly policy gradient algorithms? arXiv preprint \narXiv:1811.02553\n\n (2018)"},{"key":"35_CR7","unstructured":"Jones, T., Forrest, S.: Fitness distance correlation as a measure of problem difficulty for genetic algorithms. In: Proceedings of the 6th International Conference on Genetic Algorithms (1995)"},{"issue":"1\u20133","key":"35_CR8","first-page":"227","volume":"22","author":"S Koenig","year":"1996","unstructured":"Koenig, S., Simmons, R.G.: The effect of representation and knowledge on goal-directed exploration with reinforcement-learning algorithms. Mach. Learn. 22(1\u20133), 227\u2013250 (1996)","journal-title":"Mach. Learn."},{"key":"35_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-642-20364-0_10","volume-title":"Evolutionary Computation in Combinatorial Optimization","author":"G Lu","year":"2011","unstructured":"Lu, G., Li, J., Yao, X.: Fitness-probability cloud and a measure of problem hardness for evolutionary algorithms. In: Merz, P., Hao, J.-K. (eds.) EvoCOP 2011. LNCS, vol. 6622, pp. 108\u2013117. Springer, Heidelberg (2011). \nhttps:\/\/doi.org\/10.1007\/978-3-642-20364-0_10"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Lunacek, M., Whitley, D.: The dispersion metric and the CMA evolution strategy. In: Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation, GECCO 2006, pp. 477\u2013484. Association for Computing Machinery, New York (2006)","DOI":"10.1145\/1143997.1144085"},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"Malan, K.M., Engelbrecht, A.P.: Quantifying ruggedness of continuous landscapes using entropy. In: 2009 IEEE Congress on Evolutionary Computation, pp. 1440\u20131447 (2009)","DOI":"10.1109\/CEC.2009.4983112"},{"key":"35_CR12","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1016\/j.ins.2013.04.015","volume":"241","author":"KM Malan","year":"2013","unstructured":"Malan, K.M., Engelbrecht, A.P.: A survey of techniques for characterising fitness landscapes and some possible ways forward. Inf. Sci. 241, 148\u2013163 (2013)","journal-title":"Inf. Sci."},{"key":"35_CR13","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1613\/jair.613","volume":"11","author":"DE Moriarty","year":"1999","unstructured":"Moriarty, D.E., Schultz, A.C., Grefenstette, J.J.: Evolutionary algorithms for reinforcement learning. J. Artif. Intell. Res. 11, 241\u2013276 (1999)","journal-title":"J. Artif. Intell. Res."},{"key":"35_CR14","doi-asserted-by":"crossref","unstructured":"Ochoa, G., Tomassini, M., V\u00e9rel, S., Darabos, C.: A study of NK landscapes\u2019 basins and local optima networks. In: Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation, GECCO 2008, pp. 555\u2013562. Association for Computing Machinery, New York (2008)","DOI":"10.1145\/1389095.1389204"},{"key":"35_CR15","unstructured":"Oller, D., Glasmachers, T., Cuccu, G.: Analyzing reinforcement learning benchmarks with random weight guessing. arXiv preprint \narXiv:2004.07707\n\n (2020)"},{"key":"35_CR16","doi-asserted-by":"crossref","unstructured":"Pathak, D., Agrawal, P., Efros, A.A., Darrell, T.: Curiosity-driven exploration by self-supervised prediction. In: Proceedings of the 34th International Conference on Machine Learning (2017)","DOI":"10.1109\/CVPRW.2017.70"},{"key":"35_CR17","volume-title":"Artificial Intelligence: A Modern Approach","author":"S Russel","year":"2013","unstructured":"Russel, S., Norvig, P.: Artificial Intelligence: A Modern Approach. Pearson Education Limited, London (2013)"},{"key":"35_CR18","unstructured":"Salimans, T., Ho, J., Chen, X., Sidor, S., Sutskever, I.: Evolution strategies as a scalable alternative to reinforcement learning. arXiv preprint \narXiv:1703.03864\n\n (2017)"},{"key":"35_CR19","unstructured":"Schmidhuber, J., Hochreiter, S., Bengio, Y.: Evaluating benchmark problems by random guessing. In: Kolen, J., Cremer, S. (eds.) A Field Guide to Dynamical Recurrent Networks, pp. 231\u2013235 (2001)"},{"key":"35_CR20","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint \narXiv:1707.06347\n\n (2017)"},{"key":"35_CR21","doi-asserted-by":"crossref","unstructured":"Stapelberg, B., Malan, K.M.: Global structure of policy search spaces for reinforcement learning. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion, GECCO 2019, pp. 1773\u20131781. Association for Computing Machinery, New York (2019)","DOI":"10.1145\/3319619.3326843"},{"key":"35_CR22","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, vol. 1. MIT Press, Cambridge (1998)"},{"key":"35_CR23","unstructured":"Van Hoyweghen, C., Naudts, B.: Symmetry in the search space. In: Proceedings of the 2000 Congress on Evolutionary Computation, CEC00 (Cat. No. 00TH8512), vol. 2, pp. 1072\u20131078 (2000)"},{"key":"35_CR24","doi-asserted-by":"crossref","unstructured":"Vanneschi, L., Pirola, Y., Collard, P., Tomassini, M., Verel, S., Mauri, G.: A quantitative study of neutrality in GP Boolean landscapes. In: Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation, GECCO 2006, pp. 895\u2013902. Association for Computing Machinery, New York (2006)","DOI":"10.1145\/1143997.1144152"},{"key":"35_CR25","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1007\/978-0-387-30164-8_731","volume-title":"Encyclopedia of Machine Learning","author":"E Wiewiora","year":"2010","unstructured":"Wiewiora, E.: Reward shaping. In: Sammut, C., Webb, G.I. (eds.) Encyclopedia of Machine Learning, pp. 863\u2013865. Springer, Boston (2010). \nhttps:\/\/doi.org\/10.1007\/978-0-387-30164-8_731"},{"key":"35_CR26","doi-asserted-by":"crossref","unstructured":"Wilson, D.G., Cussat-Blanc, S., Luga, H., Miller, J.F.: Evolving simple programs for playing atari games. In: Proceedings of the Genetic and Evolutionary Computation Conference, GECCO 2018, pp. 229\u2013236. Association for Computing Machinery, New York (2018)","DOI":"10.1145\/3205455.3205578"}],"container-title":["Lecture Notes in Computer Science","Parallel Problem Solving from Nature \u2013 PPSN XVI"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58115-2_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T22:08:26Z","timestamp":1598998106000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-58115-2_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030581145","9783030581152"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58115-2_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"2 September 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PPSN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Parallel Problem Solving from Nature","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Leiden","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ppsn2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ppsn2020.liacs.leidenuniv.nl\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"268","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"99","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"37% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}