{"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/multi-goal-reinforcement-learning-challenging","title":"Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research","arxiv_id":"1802.09464","date":"2018-02-26","proceeding":null,"authors":["Matthias Plappert","Marcin Andrychowicz","Alex Ray","Bob McGrew","Bowen Baker","Glenn Powell","Jonas Schneider","Josh Tobin","Maciek Chociej","Peter Welinder","Vikash Kumar","Wojciech Zaremba"],"abstract":"The purpose of this technical report is two-fold. First of all, it introduces\na suite of challenging continuous control tasks (integrated with OpenAI Gym)\nbased on currently existing robotics hardware. The tasks include pushing,\nsliding and pick & place with a Fetch robotic arm as well as in-hand object\nmanipulation with a Shadow Dexterous Hand. All tasks have sparse binary rewards\nand follow a Multi-Goal Reinforcement Learning (RL) framework in which an agent\nis told what to do using an additional input.\n  The second part of the paper presents a set of concrete research ideas for\nimproving RL algorithms, most of which are related to Multi-Goal RL and\nHindsight Experience Replay.","url_abs":"http://arxiv.org/abs/1802.09464v2","url_pdf":"http://arxiv.org/pdf/1802.09464v2.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":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/09jvilla/CS234_gym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/1110589721/openia-gym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/Christopheraburns/openai-gym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/DartEnv/dart-env","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/EndingCredits/gym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/LucasSilve/openAIgym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/Steve--Hunter/gym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/YanglanWang/classic_control","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/YijiongLin/ITER_KER_GER","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/a-ozeki/openAI_gym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/abhiksingla/gym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/davidsonic/self_brewed_gym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/developer-smartwebzone/-reinforcement-learning-algorithms.","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/flowersteam/curious","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/gtrll/dartenv","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/jturner65/Getup-DartEnv","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/ligy2016/gym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/mbrucker07/experiments","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/nmsquared/CS7641-Assignment-4","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/nohboogy/gym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/ozcell/gym_wmgds_ma","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/shinian123/gym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/shriram2112/Reinforcement_learning_gym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/tjcdev/mlpgym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/tsinghua-rll/gym-gridworld","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/varuncs2011/rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/vvanirudh/imitation-learning-gym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multi-goal-reinforcement-learning-challenging","repo_url":"https://github.com/zubair-irshad/imitation_learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"multi-goal-reinforcement-learning","task_name":"Multi-Goal Reinforcement Learning"},{"task_slug":"openai-gym","task_name":"OpenAI Gym"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"continuous-control","task_name":"continuous-control"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"experience-replay","method_name":"Experience Replay"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/reinforcement-learning-rl-on-1","task":"Reinforcement Learning (RL)","dataset":".","model":".","rank_in_archive_order":1,"of":1,"metrics":{"0..5sec":"."},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.09464","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}