{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:09:42Z","timestamp":1750219782860,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":7,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,15]],"date-time":"2023-07-15T00:00:00Z","timestamp":1689379200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,15]]},"DOI":"10.1145\/3583133.3590610","type":"proceedings-article","created":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T23:30:33Z","timestamp":1690241433000},"page":"351-354","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Evolution of an Internal Reward Function for Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1421-3667","authenticated-orcid":false,"given":"Weiyi","family":"Zuo","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7884-9432","authenticated-orcid":false,"given":"Joachim","family":"Pedersen","sequence":"additional","affiliation":[{"name":"IT University of Copenhagen, Copenhagen, Denmark"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3607-8400","authenticated-orcid":false,"given":"Sebastian","family":"Risi","sequence":"additional","affiliation":[{"name":"IT University of Copenhagen, Copenhagen, Denmark"}]}],"member":"320","published-online":{"date-parts":[[2023,7,24]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Genloco: Generalized locomotion controllers for quadrupedal robots. arXiv preprint arXiv:2209.05309","author":"Feng Gilbert","year":"2022","unstructured":"Gilbert Feng , Hongbo Zhang , 2022 . Genloco: Generalized locomotion controllers for quadrupedal robots. arXiv preprint arXiv:2209.05309 (2022). Gilbert Feng, Hongbo Zhang, et al. 2022. Genloco: Generalized locomotion controllers for quadrupedal robots. arXiv preprint arXiv:2209.05309 (2022)."},{"key":"e_1_3_2_1_2_1","volume-title":"The CMA evolution strategy: a comparing review. Towards a new evolutionary computation","author":"Hansen Nikolaus","year":"2006","unstructured":"Nikolaus Hansen . 2006. The CMA evolution strategy: a comparing review. Towards a new evolutionary computation ( 2006 ), 75--102. Nikolaus Hansen. 2006. The CMA evolution strategy: a comparing review. Towards a new evolutionary computation (2006), 75--102."},{"key":"e_1_3_2_1_3_1","unstructured":"Louis Kirsch James Harrison etal 2022. General-purpose in-context learning by meta-learning transformers. arXiv preprint arXiv:2212.04458 (2022).  Louis Kirsch James Harrison et al. 2022. General-purpose in-context learning by meta-learning transformers. arXiv preprint arXiv:2212.04458 (2022)."},{"key":"e_1_3_2_1_4_1","volume-title":"Evolving and merging hebbian learning rules: increasing generalization by decreasing the number of rules. arXiv preprint arXiv:2104.07959","author":"Pedersen Joachim Winther","year":"2021","unstructured":"Joachim Winther Pedersen and Sebastian Risi . 2021. Evolving and merging hebbian learning rules: increasing generalization by decreasing the number of rules. arXiv preprint arXiv:2104.07959 ( 2021 ). Joachim Winther Pedersen and Sebastian Risi. 2021. Evolving and merging hebbian learning rules: increasing generalization by decreasing the number of rules. arXiv preprint arXiv:2104.07959 (2021)."},{"key":"e_1_3_2_1_5_1","unstructured":"John Schulman Filip Wolski etal 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017).  John Schulman Filip Wolski et al. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_1_6_1","volume-title":"A walk in the park: Learning to walk in 20 minutes with model-free reinforcement learning. arXiv preprint arXiv:2208.07860","author":"Smith Laura","year":"2022","unstructured":"Laura Smith , Ilya Kostrikov , and Sergey Levine . 2022. A walk in the park: Learning to walk in 20 minutes with model-free reinforcement learning. arXiv preprint arXiv:2208.07860 ( 2022 ). Laura Smith, Ilya Kostrikov, and Sergey Levine. 2022. A walk in the park: Learning to walk in 20 minutes with model-free reinforcement learning. arXiv preprint arXiv:2208.07860 (2022)."},{"key":"e_1_3_2_1_7_1","unstructured":"Xingyou Song Yiding Jiang etal 2019. Observational overfitting in reinforcement learning. arXiv preprint arXiv:1912.02975 (2019).  Xingyou Song Yiding Jiang et al. 2019. Observational overfitting in reinforcement learning. arXiv preprint arXiv:1912.02975 (2019)."}],"event":{"name":"GECCO '23 Companion: Companion Conference on Genetic and Evolutionary Computation","sponsor":["SIGEVO ACM Special Interest Group on Genetic and Evolutionary Computation"],"location":"Lisbon Portugal","acronym":"GECCO '23 Companion"},"container-title":["Proceedings of the Companion Conference on Genetic and Evolutionary Computation"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583133.3590610","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3583133.3590610","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:45Z","timestamp":1750178265000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583133.3590610"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,15]]},"references-count":7,"alternative-id":["10.1145\/3583133.3590610","10.1145\/3583133"],"URL":"https:\/\/doi.org\/10.1145\/3583133.3590610","relation":{},"subject":[],"published":{"date-parts":[[2023,7,15]]},"assertion":[{"value":"2023-07-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}