{"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/phyre-a-new-benchmark-for-physical-reasoning","title":"PHYRE: A New Benchmark for Physical Reasoning","arxiv_id":"1908.05656","date":"2019-08-15","proceeding":"NeurIPS 2019 12","authors":["Anton Bakhtin","Laurens van der Maaten","Justin Johnson","Laura Gustafson","Ross Girshick"],"abstract":"Understanding and reasoning about physics is an important ability of intelligent agents. We develop the PHYRE benchmark for physical reasoning that contains a set of simple classical mechanics puzzles in a 2D physical environment. The benchmark is designed to encourage the development of learning algorithms that are sample-efficient and generalize well across puzzles. We test several modern learning algorithms on PHYRE and find that these algorithms fall short in solving the puzzles efficiently. We expect that PHYRE will encourage the development of novel sample-efficient agents that learn efficient but useful models of physics. For code and to play PHYRE for yourself, please visit https://player.phyre.ai.","url_abs":"https://arxiv.org/abs/1908.05656v1","url_pdf":"https://arxiv.org/pdf/1908.05656v1.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":"phyre-a-new-benchmark-for-physical-reasoning","repo_url":"https://github.com/facebookresearch/phyre","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"phyre-a-new-benchmark-for-physical-reasoning","repo_url":"https://github.com/ndrwmlnk/awesome-benchmarks-for-physical-reasoning-ai","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[],"datasets_introduced":[{"slug":"phyre","name":"PHYRE","full_name":"PHYsical REasoning"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-reasoning-on-phyre-1b-cross","task":"Visual Reasoning","dataset":"PHYRE-1B-Cross","model":"DQN","rank_in_archive_order":4,"of":4,"metrics":{"AUCCESS":"36.8"},"uses_additional_data":false},{"leaderboard":"/sota/visual-reasoning-on-phyre-1b-within","task":"Visual Reasoning","dataset":"PHYRE-1B-Within","model":"DQN","rank_in_archive_order":4,"of":4,"metrics":{"AUCCESS":"77.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1908.05656","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}