{"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/deep-recurrent-q-learning-vs-deep-q-learning","title":"Deep Recurrent Q-Learning vs Deep Q-Learning on a simple Partially Observable Markov Decision Process with Minecraft","arxiv_id":"1903.04311","date":"2019-03-11","proceeding":null,"authors":["Clément Romac","Vincent Béraud"],"abstract":"Deep Q-Learning has been successfully applied to a wide variety of tasks in\nthe past several years. However, the architecture of the vanilla Deep Q-Network\nis not suited to deal with partially observable environments such as 3D video\ngames. For this, recurrent layers have been added to the Deep Q-Network in\norder to allow it to handle past dependencies. We here use Minecraft for its\ncustomization advantages and design two very simple missions that can be frames\nas Partially Observable Markov Decision Process. We compare on these missions\nthe Deep Q-Network and the Deep Recurrent Q-Network in order to see if the\nlatter, which is trickier and longer to train, is always the best architecture\nwhen the agent has to deal with partial observability.","url_abs":"http://arxiv.org/abs/1903.04311v2","url_pdf":"http://arxiv.org/pdf/1903.04311v2.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":"deep-recurrent-q-learning-vs-deep-q-learning","repo_url":"https://github.com/vincentberaud/Minecraft-Reinforcement-Learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-recurrent-q-learning-vs-deep-q-learning","repo_url":"https://github.com/rishavb123/MineRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"minecraft","task_name":"Minecraft"},{"task_slug":"q-learning","task_name":"Q-Learning"}],"methods":[{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}