{"title":"漩涡:一个加速器兼容的GP框架","authors":"Deacon Seals, Robert Wilkes, D. Tauritz","doi":"10.1145/3583133.3596359","DOIUrl":null,"url":null,"abstract":"This work presents the Maelstrom framework for strong-typed tree GP. Maelstrom is a Python library designed to facilitate rapid prototyping and exploration of weak-typed tree GP, strong-typed tree GP, island model, and coevolution with flexibility that enables support for accelerator frameworks such as JAX. The architecture and features of Maelstrom are discussed alongside several example applications employing Gym environments and an accelerated version of predator-prey.","PeriodicalId":422029,"journal":{"name":"Proceedings of the Companion Conference on Genetic and Evolutionary Computation","volume":"159 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Maelstrom: An Accelerator-compatible GP Framework\",\"authors\":\"Deacon Seals, Robert Wilkes, D. Tauritz\",\"doi\":\"10.1145/3583133.3596359\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This work presents the Maelstrom framework for strong-typed tree GP. Maelstrom is a Python library designed to facilitate rapid prototyping and exploration of weak-typed tree GP, strong-typed tree GP, island model, and coevolution with flexibility that enables support for accelerator frameworks such as JAX. The architecture and features of Maelstrom are discussed alongside several example applications employing Gym environments and an accelerated version of predator-prey.\",\"PeriodicalId\":422029,\"journal\":{\"name\":\"Proceedings of the Companion Conference on Genetic and Evolutionary Computation\",\"volume\":\"159 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-07-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the Companion Conference on Genetic and Evolutionary Computation\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3583133.3596359\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the Companion Conference on Genetic and Evolutionary Computation","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3583133.3596359","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
This work presents the Maelstrom framework for strong-typed tree GP. Maelstrom is a Python library designed to facilitate rapid prototyping and exploration of weak-typed tree GP, strong-typed tree GP, island model, and coevolution with flexibility that enables support for accelerator frameworks such as JAX. The architecture and features of Maelstrom are discussed alongside several example applications employing Gym environments and an accelerated version of predator-prey.