{"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/self-supervised-learning-of-image-embedding","title":"Self-supervised Learning of Image Embedding for Continuous Control","arxiv_id":"1901.00943","date":"2019-01-03","proceeding":null,"authors":["Carlos Florensa","Jonas Degrave","Nicolas Heess","Jost Tobias Springenberg","Martin Riedmiller"],"abstract":"Operating directly from raw high dimensional sensory inputs like images is\nstill a challenge for robotic control. Recently, Reinforcement Learning methods\nhave been proposed to solve specific tasks end-to-end, from pixels to torques.\nHowever, these approaches assume the access to a specified reward which may\nrequire specialized instrumentation of the environment. Furthermore, the\nobtained policy and representations tend to be task specific and may not\ntransfer well. In this work we investigate completely self-supervised learning\nof a general image embedding and control primitives, based on finding the\nshortest time to reach any state. We also introduce a new structure for the\nstate-action value function that builds a connection between model-free and\nmodel-based methods, and improves the performance of the learning algorithm. We\nexperimentally demonstrate these findings in three simulated robotic tasks.","url_abs":"http://arxiv.org/abs/1901.00943v1","url_pdf":"http://arxiv.org/pdf/1901.00943v1.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":"self-supervised-learning-of-image-embedding","repo_url":"https://github.com/subinlab/model_based_rl_paper","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"continuous-control","task_name":"continuous-control"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.00943","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}