{"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/black-box-data-efficient-policy-search-for","title":"Black-Box Data-efficient Policy Search for Robotics","arxiv_id":"1703.07261","date":"2017-03-21","proceeding":null,"authors":["Konstantinos Chatzilygeroudis","Roberto Rama","Rituraj Kaushik","Dorian Goepp","Vassilis Vassiliades","Jean-Baptiste Mouret"],"abstract":"The most data-efficient algorithms for reinforcement learning (RL) in\nrobotics are based on uncertain dynamical models: after each episode, they\nfirst learn a dynamical model of the robot, then they use an optimization\nalgorithm to find a policy that maximizes the expected return given the model\nand its uncertainties. It is often believed that this optimization can be\ntractable only if analytical, gradient-based algorithms are used; however,\nthese algorithms require using specific families of reward functions and\npolicies, which greatly limits the flexibility of the overall approach. In this\npaper, we introduce a novel model-based RL algorithm, called Black-DROPS\n(Black-box Data-efficient RObot Policy Search) that: (1) does not impose any\nconstraint on the reward function or the policy (they are treated as\nblack-boxes), (2) is as data-efficient as the state-of-the-art algorithm for\ndata-efficient RL in robotics, and (3) is as fast (or faster) than analytical\napproaches when several cores are available. The key idea is to replace the\ngradient-based optimization algorithm with a parallel, black-box algorithm that\ntakes into account the model uncertainties. We demonstrate the performance of\nour new algorithm on two standard control benchmark problems (in simulation)\nand a low-cost robotic manipulator (with a real robot).","url_abs":"http://arxiv.org/abs/1703.07261v2","url_pdf":"http://arxiv.org/pdf/1703.07261v2.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":"black-box-data-efficient-policy-search-for","repo_url":"https://github.com/resibots/blackdrops","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.07261","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}