{"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/some-considerations-on-learning-to-explore","title":"Some Considerations on Learning to Explore via Meta-Reinforcement Learning","arxiv_id":"1803.01118","date":"2018-03-03","proceeding":"ICLR 2018 1","authors":["Bradly C. Stadie","Ge Yang","Rein Houthooft","Xi Chen","Yan Duan","Yuhuai Wu","Pieter Abbeel","Ilya Sutskever"],"abstract":"We consider the problem of exploration in meta reinforcement learning. Two\nnew meta reinforcement learning algorithms are suggested: E-MAML and\nE-$\\text{RL}^2$. Results are presented on a novel environment we call `Krazy\nWorld' and a set of maze environments. We show E-MAML and E-$\\text{RL}^2$\ndeliver better performance on tasks where exploration is important.","url_abs":"http://arxiv.org/abs/1803.01118v2","url_pdf":"http://arxiv.org/pdf/1803.01118v2.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":"some-considerations-on-learning-to-explore","repo_url":"https://github.com/episodeyang/e-maml","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"some-considerations-on-learning-to-explore","repo_url":"https://github.com/Zhiwei-Z/PrompLimitTest","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"some-considerations-on-learning-to-explore","repo_url":"https://github.com/Zhiwei-Z/SeqPromp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"some-considerations-on-learning-to-explore","repo_url":"https://github.com/Zhiwei-Z/prompzzw","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"some-considerations-on-learning-to-explore","repo_url":"https://github.com/clrrrr/promp_plus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"some-considerations-on-learning-to-explore","repo_url":"https://github.com/jonasrothfuss/promp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"some-considerations-on-learning-to-explore","repo_url":"https://github.com/mazpie/mime","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"meta-reinforcement-learning","task_name":"Meta Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.01118","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}