{"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/faster-reinforcement-learning-using-active","title":"Faster Reinforcement Learning Using Active Simulators","arxiv_id":"1703.07853","date":"2017-03-22","proceeding":null,"authors":["Vikas Jain","Theja Tulabandhula"],"abstract":"In this work, we propose several online methods to build a \\emph{learning\ncurriculum} from a given set of target-task-specific training tasks in order to\nspeed up reinforcement learning (RL). These methods can decrease the total\ntraining time needed by an RL agent compared to training on the target task\nfrom scratch. Unlike traditional transfer learning, we consider creating a\nsequence from several training tasks in order to provide the most benefit in\nterms of reducing the total time to train.\n  Our methods utilize the learning trajectory of the agent on the curriculum\ntasks seen so far to decide which tasks to train on next. An attractive feature\nof our methods is that they are weakly coupled to the choice of the RL\nalgorithm as well as the transfer learning method. Further, when there is\ndomain information available, our methods can incorporate such knowledge to\nfurther speed up the learning. We experimentally show that these methods can be\nused to obtain suitable learning curricula that speed up the overall training\ntime on two different domains.","url_abs":"http://arxiv.org/abs/1703.07853v2","url_pdf":"http://arxiv.org/pdf/1703.07853v2.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":"faster-reinforcement-learning-using-active","repo_url":"https://github.com/thejat/active-curricula-for-efficient-reinforcement-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}