{"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/implementing-the-deep-q-network","title":"Implementing the Deep Q-Network","arxiv_id":"1711.07478","date":"2017-11-20","proceeding":null,"authors":["Melrose Roderick","James Macglashan","Stefanie Tellex"],"abstract":"The Deep Q-Network proposed by Mnih et al. [2015] has become a benchmark and\nbuilding point for much deep reinforcement learning research. However,\nreplicating results for complex systems is often challenging since original\nscientific publications are not always able to describe in detail every\nimportant parameter setting and software engineering solution. In this paper,\nwe present results from our work reproducing the results of the DQN paper. We\nhighlight key areas in the implementation that were not covered in great detail\nin the original paper to make it easier for researchers to replicate these\nresults, including termination conditions and gradient descent algorithms.\nFinally, we discuss methods for improving the computational performance and\nprovide our own implementation that is designed to work with a range of\ndomains, and not just the original Arcade Learning Environment [Bellemare et\nal., 2013].","url_abs":"http://arxiv.org/abs/1711.07478v1","url_pdf":"http://arxiv.org/pdf/1711.07478v1.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":"implementing-the-deep-q-network","repo_url":"https://github.com/xgfelicia/Reinforcement-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dqn","method_name":"DQN"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.07478","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}