{"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/investigating-human-priors-for-playing-video","title":"Investigating Human Priors for Playing Video Games","arxiv_id":"1802.10217","date":"2018-02-28","proceeding":"ICML 2018 7","authors":["Rachit Dubey","Pulkit Agrawal","Deepak Pathak","Thomas L. Griffiths","Alexei A. Efros"],"abstract":"What makes humans so good at solving seemingly complex video games? Unlike\ncomputers, humans bring in a great deal of prior knowledge about the world,\nenabling efficient decision making. This paper investigates the role of human\npriors for solving video games. Given a sample game, we conduct a series of\nablation studies to quantify the importance of various priors on human\nperformance. We do this by modifying the video game environment to\nsystematically mask different types of visual information that could be used by\nhumans as priors. We find that removal of some prior knowledge causes a drastic\ndegradation in the speed with which human players solve the game, e.g. from 2\nminutes to over 20 minutes. Furthermore, our results indicate that general\npriors, such as the importance of objects and visual consistency, are critical\nfor efficient game-play. Videos and the game manipulations are available at\nhttps://rach0012.github.io/humanRL_website/","url_abs":"http://arxiv.org/abs/1802.10217v3","url_pdf":"http://arxiv.org/pdf/1802.10217v3.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":"investigating-human-priors-for-playing-video","repo_url":"https://github.com/rach0012/humanRL_prior_games","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.10217","atlas_url":"https://app.syntology.ai/?focus=1802.10217","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}