{"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/schema-networks-zero-shot-transfer-with-a","title":"Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics","arxiv_id":"1706.04317","date":"2017-06-14","proceeding":"ICML 2017 8","authors":["Ken Kansky","Tom Silver","David A. Mély","Mohamed Eldawy","Miguel Lázaro-Gredilla","Xinghua Lou","Nimrod Dorfman","Szymon Sidor","Scott Phoenix","Dileep George"],"abstract":"The recent adaptation of deep neural network-based methods to reinforcement\nlearning and planning domains has yielded remarkable progress on individual\ntasks. Nonetheless, progress on task-to-task transfer remains limited. In\npursuit of efficient and robust generalization, we introduce the Schema\nNetwork, an object-oriented generative physics simulator capable of\ndisentangling multiple causes of events and reasoning backward through causes\nto achieve goals. The richly structured architecture of the Schema Network can\nlearn the dynamics of an environment directly from data. We compare Schema\nNetworks with Asynchronous Advantage Actor-Critic and Progressive Networks on a\nsuite of Breakout variations, reporting results on training efficiency and\nzero-shot generalization, consistently demonstrating faster, more robust\nlearning and better transfer. We argue that generalizing from limited data and\nlearning causal relationships are essential abilities on the path toward\ngenerally intelligent systems.","url_abs":"http://arxiv.org/abs/1706.04317v2","url_pdf":"http://arxiv.org/pdf/1706.04317v2.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":"schema-networks-zero-shot-transfer-with-a","repo_url":"https://github.com/mzhao98/DeepQLearning_CrossyRoad","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"schema-networks-zero-shot-transfer-with-a","repo_url":"https://github.com/phigley/taxi","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"zero-shot-generalization","task_name":"Zero-shot Generalization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.04317","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}