We introduce AlphaD3M, an automatic machine learning (AutoML) system based on meta reinforcement learning using sequence models with self play. AlphaD3M is based on edit operations performed over machine learning pipeline primitives providing explainability. We compare AlphaD3M with state-of-the-art AutoML systems: Autosklearn, Autostacker, and TPOT, on OpenML datasets. AlphaD3M achieves competitive performance while being an order of magnitude faster, reducing computation time from hours to minutes, and is explainable by design.
Drori, Iddo, Krishnamurthy, Yamuna, Rampin, Remi, Lourenco, Raoni de Paula, Ono, Jorge Piazentin, Cho, Kyunghyun, Silva, Claudio, Freire, Juliana
Automatic machine learning is an important problem in the forefront of machine learning. The strongest AutoML systems are based on neural networks, evolutionary algorithms, and Bayesian optimization. Recently AlphaD3M reached state-of-the-art results with an order of magnitude speedup using reinforcement learning with self-play. In this work we extend AlphaD3M by using a pipeline grammar and a pre-trained model which generalizes from many different datasets and similar tasks. Our results demonstrate improved performance compared with our earlier work and existing methods on AutoML benchmark datasets for classification and regression tasks. In
Drori, Iddo, Krishnamurthy, Yamuna, Lourenco, Raoni, Rampin, Remi, Cho, Kyunghyun, Silva, Claudio, Freire, Juliana
Research paper by Alan G. Paredes Cetina and collaborators. arXiv record dated 2025-11-24. Research area: Machine learning.
Alan G. Paredes Cetina, Kaouther Benguessoum, Raoni Lourenço, Sylvain Kubler
Research paper by Roberto Molinaro and collaborators. arXiv record dated 2025-02-03. Research area: Machine learning.
Roberto Molinaro, Samuel Lanthaler, Bogdan Raonić, Tobias Rohner, Victor Armegioiu, Stephan Simonis, Dana Grund, Yannick Ramic, Zhong Yi Wan, Fei Sha, Siddhartha Mishra, Leonardo Zepeda-Núñez
Research paper by Takashi Furuya and collaborators. arXiv record dated 2025-11-03. Research area: Machine learning.
Takashi Furuya, Anastasis Kratsios, Dylan Possamaï, Bogdan Raonić
Research paper by Semin Kim and collaborators, published 2026 in arXiv (Cornell University). Research area: Speech Recognition and Synthesis.
Semin Kim, Seungjun Chung, Taehong Moon, Sangheon Lee, Minsu Ahn, Keon Lee, Nam Hyung Kim, Jaewoong Cho, Ludwig Schmidt, Kangwook Lee, Dongmin Park
Research paper by Beomsoo Kim and collaborators. arXiv record dated 2026-04-08. Research area: Language technology.
Beomsoo Kim, Changho Choi, Dohyun Kim, Dongki Lee, Ethan Ewer, Eunchong Kim, Gyeongman Kim, Haechan Kim, Hyeonghwan Kim, Inkyu Park, Jihun Yun, Jihwan Moon, Jiyun Kim, Joonghyun Bae, Junhyuck Kim, Minkyu Kim, Sehun Lee, Seungjun Chung, Sungwoo Cho, Dongmin Park, Dongwon Kim, Hara Kang, Jonghyun Lee, Keon Lee, Kangwook Lee, Jaewoong Cho
Research paper by Sepehr Mousavi and collaborators. arXiv record dated 2025-10-14. Research area: Machine learning.
Sepehr Mousavi, Shizheng Wen, Levi Lingsch, Maximilian Herde, Bogdan Raonić, Siddhartha Mishra
Research paper by Orestis Oikonomou and collaborators. arXiv record dated 2026-10-31. Research area: Machine learning.
Orestis Oikonomou, Bogdan Raonic
Research paper by Bogdan Raonić and collaborators. arXiv record dated 2026-05-11. Research area: Machine learning.
Bogdan Raonić, Siddhartha Mishra, Samuel Lanthaler
