{"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/learning-to-play-general-video-games-via-an","title":"Learning to Play General Video-Games via an Object Embedding Network","arxiv_id":"1803.05262","date":"2018-03-14","proceeding":null,"authors":["William Woof","Ke Chen"],"abstract":"Deep reinforcement learning (DRL) has proven to be an effective tool for\ncreating general video-game AI. However most current DRL video-game agents\nlearn end-to-end from the video-output of the game, which is superfluous for\nmany applications and creates a number of additional problems. More\nimportantly, directly working on pixel-based raw video data is substantially\ndistinct from what a human player does.In this paper, we present a novel method\nwhich enables DRL agents to learn directly from object information. This is\nobtained via use of an object embedding network (OEN) that compresses a set of\nobject feature vectors of different lengths into a single fixed-length unified\nfeature vector representing the current game-state and fulfills the DRL\nsimultaneously. We evaluate our OEN-based DRL agent by comparing to several\nstate-of-the-art approaches on a selection of games from the GVG-AI\nCompetition. Experimental results suggest that our object-based DRL agent\nyields performance comparable to that of those approaches used in our\ncomparative study.","url_abs":"http://arxiv.org/abs/1803.05262v2","url_pdf":"http://arxiv.org/pdf/1803.05262v2.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":"learning-to-play-general-video-games-via-an","repo_url":"https://github.com/EndingCredits/Object-Based-RL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}