{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dynamic-algorithm-configuration-foundation-of","title":"Dynamic Algorithm Configuration: Foundation of a New Meta-Algorithmic Framework","arxiv_id":null,"date":"2020-06-01","proceeding":null,"authors":["André Biedenkapp","H. Furkan Bozkurt","Theresa Eimer","Frank Hutter","Marius Lindauer"],"abstract":"The  performance  of  many  algorithms  in  the  fields  of hard combinatorial problem solving, machine learning or AI in general  depends  on  parameter  tuning.  Automated  methods  have  been proposed to alleviate users from the tedious and error-prone task of manually searching for performance-optimized configurations across a set of problem instances. However, there is still a lot of untapped potential through adjusting an algorithm’s parameters online since different parameter values can be optimal at different stages of the algorithm. Prior work showed that reinforcement learning is an effective approach to learn policies for online adjustments of algorithm parameters in a data-driven way. We extend that approach by formulating the resulting dynamic algorithm configuration as a contextual MDP, such that RL not only learns a policy for a single instance, but across a set of instances. To lay the foundation for studying dynamic algorithm configuration with RL in a controlled setting, we propose white-box benchmarks covering major aspects that make dynamic algorithm configuration a hard problem in practice and study the performance of various types of configuration strategies for them. On these white-box benchmarks, we show that (i) RL is a robust candidate for learning configuration policies, outperforming standard parameter optimization approaches, such as classical algorithm configuration; (ii) based on function approximation, RL agents can learn to generalize to new types of instances; and (iii) self-paced learning can substantially improve the performance by selecting a useful sequence of training instances automatically.","url_abs":"http://ecai2020.eu/papers/1237_paper.pdf","url_pdf":"http://ecai2020.eu/papers/1237_paper.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dynamic-algorithm-configuration-foundation-of","repo_url":"https://github.com/automl/DAC","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"general-reinforcement-learning","task_name":"General Reinforcement Learning"}],"methods":[{"method_slug":"dac","method_name":"DAC"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"double-dqn","method_name":"Double DQN"},{"method_slug":"double-q-learning","method_name":"Double Q-learning"},{"method_slug":"experience-replay","method_name":"Experience Replay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}