{"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/learnings-options-end-to-end-for-continuous","title":"Learnings Options End-to-End for Continuous Action Tasks","arxiv_id":"1712.00004","date":"2017-11-30","proceeding":null,"authors":["Martin Klissarov","Pierre-Luc Bacon","Jean Harb","Doina Precup"],"abstract":"We present new results on learning temporally extended actions for\ncontinuoustasks, using the options framework (Suttonet al.[1999b], Precup\n[2000]). In orderto achieve this goal we work with the option-critic\narchitecture (Baconet al.[2017])using a deliberation cost and train it with\nproximal policy optimization (Schulmanet al.[2017]) instead of vanilla policy\ngradient. Results on Mujoco domains arepromising, but lead to interesting\nquestions aboutwhena given option should beused, an issue directly connected to\nthe use of initiation sets.","url_abs":"http://arxiv.org/abs/1712.00004v1","url_pdf":"http://arxiv.org/pdf/1712.00004v1.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":"learnings-options-end-to-end-for-continuous","repo_url":"https://github.com/mklissa/PPOC","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"learnings-options-end-to-end-for-continuous","repo_url":"https://github.com/kkhetarpal/ioc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"learnings-options-end-to-end-for-continuous","repo_url":"https://github.com/shuishida/soaprl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"mujoco","task_name":"MuJoCo"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1712.00004","atlas_url":"https://app.syntology.ai/?focus=1712.00004","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}