{"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-reinforcement-learning-with-a-natural","title":"Deep Reinforcement Learning with a Natural Language Action Space","arxiv_id":"1511.04636","date":"2015-11-14","proceeding":"ACL 2016 8","authors":["Ji He","Jianshu Chen","Xiaodong He","Jianfeng Gao","Lihong Li","Li Deng","Mari Ostendorf"],"abstract":"This paper introduces a novel architecture for reinforcement learning with\ndeep neural networks designed to handle state and action spaces characterized\nby natural language, as found in text-based games. Termed a deep reinforcement\nrelevance network (DRRN), the architecture represents action and state spaces\nwith separate embedding vectors, which are combined with an interaction\nfunction to approximate the Q-function in reinforcement learning. We evaluate\nthe DRRN on two popular text games, showing superior performance over other\ndeep Q-learning architectures. Experiments with paraphrased action descriptions\nshow that the model is extracting meaning rather than simply memorizing strings\nof text.","url_abs":"http://arxiv.org/abs/1511.04636v5","url_pdf":"http://arxiv.org/pdf/1511.04636v5.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-reinforcement-learning-with-a-natural","repo_url":"https://github.com/MikulasZelinka/pyfiction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"deep-reinforcement-learning-with-a-natural","repo_url":"https://github.com/jvking/text-games","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-reinforcement-learning-with-a-natural","repo_url":"https://github.com/matthewsparr/Deep-Zork","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"q-learning","task_name":"Q-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"},{"task_slug":"text-based-games","task_name":"text-based games"}],"methods":[{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1511.04636","atlas_url":"https://app.syntology.ai/?focus=1511.04636","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}