{"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/action-conditional-video-prediction-using","title":"Action-Conditional Video Prediction using Deep Networks in Atari Games","arxiv_id":"1507.08750","date":"2015-07-31","proceeding":"NeurIPS 2015 12","authors":["Junhyuk Oh","Xiaoxiao Guo","Honglak Lee","Richard Lewis","Satinder Singh"],"abstract":"Motivated by vision-based reinforcement learning (RL) problems, in particular\nAtari games from the recent benchmark Aracade Learning Environment (ALE), we\nconsider spatio-temporal prediction problems where future (image-)frames are\ndependent on control variables or actions as well as previous frames. While not\ncomposed of natural scenes, frames in Atari games are high-dimensional in size,\ncan involve tens of objects with one or more objects being controlled by the\nactions directly and many other objects being influenced indirectly, can\ninvolve entry and departure of objects, and can involve deep partial\nobservability. We propose and evaluate two deep neural network architectures\nthat consist of encoding, action-conditional transformation, and decoding\nlayers based on convolutional neural networks and recurrent neural networks.\nExperimental results show that the proposed architectures are able to generate\nvisually-realistic frames that are also useful for control over approximately\n100-step action-conditional futures in some games. To the best of our\nknowledge, this paper is the first to make and evaluate long-term predictions\non high-dimensional video conditioned by control inputs.","url_abs":"http://arxiv.org/abs/1507.08750v2","url_pdf":"http://arxiv.org/pdf/1507.08750v2.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":"action-conditional-video-prediction-using","repo_url":"https://github.com/yogi2578/GameEngineLearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"video-prediction","task_name":"Video Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1507.08750","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}