{"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/playing-fps-games-with-deep-reinforcement","title":"Playing FPS Games with Deep Reinforcement Learning","arxiv_id":"1609.05521","date":"2016-09-18","proceeding":null,"authors":["Guillaume Lample","Devendra Singh Chaplot"],"abstract":"Advances in deep reinforcement learning have allowed autonomous agents to\nperform well on Atari games, often outperforming humans, using only raw pixels\nto make their decisions. However, most of these games take place in 2D\nenvironments that are fully observable to the agent. In this paper, we present\nthe first architecture to tackle 3D environments in first-person shooter games,\nthat involve partially observable states. Typically, deep reinforcement\nlearning methods only utilize visual input for training. We present a method to\naugment these models to exploit game feature information such as the presence\nof enemies or items, during the training phase. Our model is trained to\nsimultaneously learn these features along with minimizing a Q-learning\nobjective, which is shown to dramatically improve the training speed and\nperformance of our agent. Our architecture is also modularized to allow\ndifferent models to be independently trained for different phases of the game.\nWe show that the proposed architecture substantially outperforms built-in AI\nagents of the game as well as humans in deathmatch scenarios.","url_abs":"http://arxiv.org/abs/1609.05521v2","url_pdf":"http://arxiv.org/pdf/1609.05521v2.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":"playing-fps-games-with-deep-reinforcement","repo_url":"https://github.com/glample/Arnold","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"playing-fps-games-with-deep-reinforcement","repo_url":"https://github.com/KyleChen400/patch_dqn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"playing-fps-games-with-deep-reinforcement","repo_url":"https://github.com/RENHANFEI/patch_sup","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"playing-fps-games-with-deep-reinforcement","repo_url":"https://github.com/RENHANFEI/vizdoom_health_gathering","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"playing-fps-games-with-deep-reinforcement","repo_url":"https://github.com/RENHANFEI/vizdoom_patch_dqn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"playing-fps-games-with-deep-reinforcement","repo_url":"https://github.com/RENHANFEI/vizdoom_patch_supreme","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"playing-fps-games-with-deep-reinforcement","repo_url":"https://github.com/jeffchy/Artificial-Idiot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"fps-games","task_name":"FPS Games"},{"task_slug":"game-of-doom","task_name":"Game of Doom"},{"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"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1609.05521","atlas_url":"https://app.syntology.ai/?focus=1609.05521","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}