{"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/state-representation-learning-for-control-an","title":"State Representation Learning for Control: An Overview","arxiv_id":"1802.04181","date":"2018-02-12","proceeding":null,"authors":["Timothée Lesort","Natalia Díaz-Rodríguez","Jean-François Goudou","David Filliat"],"abstract":"Representation learning algorithms are designed to learn abstract features\nthat characterize data. State representation learning (SRL) focuses on a\nparticular kind of representation learning where learned features are in low\ndimension, evolve through time, and are influenced by actions of an agent. The\nrepresentation is learned to capture the variation in the environment generated\nby the agent's actions; this kind of representation is particularly suitable\nfor robotics and control scenarios. In particular, the low dimension\ncharacteristic of the representation helps to overcome the curse of\ndimensionality, provides easier interpretation and utilization by humans and\ncan help improve performance and speed in policy learning algorithms such as\nreinforcement learning.\n  This survey aims at covering the state-of-the-art on state representation\nlearning in the most recent years. It reviews different SRL methods that\ninvolve interaction with the environment, their implementations and their\napplications in robotics control tasks (simulated or real). In particular, it\nhighlights how generic learning objectives are differently exploited in the\nreviewed algorithms. Finally, it discusses evaluation methods to assess the\nrepresentation learned and summarizes current and future lines of research.","url_abs":"http://arxiv.org/abs/1802.04181v2","url_pdf":"http://arxiv.org/pdf/1802.04181v2.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":"state-representation-learning-for-control-an","repo_url":"https://github.com/araffin/srl-zoo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.04181","atlas_url":"https://app.syntology.ai/?focus=1802.04181","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}