{"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/variational-deep-q-network","title":"Variational Deep Q Network","arxiv_id":"1711.11225","date":"2017-11-30","proceeding":null,"authors":["Yunhao Tang","Alp Kucukelbir"],"abstract":"We propose a framework that directly tackles the probability distribution of\nthe value function parameters in Deep Q Network (DQN), with powerful\nvariational inference subroutines to approximate the posterior of the\nparameters. We will establish the equivalence between our proposed surrogate\nobjective and variational inference loss. Our new algorithm achieves efficient\nexploration and performs well on large scale chain Markov Decision Process\n(MDP).","url_abs":"http://arxiv.org/abs/1711.11225v1","url_pdf":"http://arxiv.org/pdf/1711.11225v1.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":"variational-deep-q-network","repo_url":"https://github.com/HarriBellThomas/VDQN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"efficient-exploration","task_name":"Efficient Exploration"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.11225","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}