{"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/natural-environment-benchmarks-for","title":"Natural Environment Benchmarks for Reinforcement Learning","arxiv_id":"1811.06032","date":"2018-11-14","proceeding":null,"authors":["Amy Zhang","Yuxin Wu","Joelle Pineau"],"abstract":"While current benchmark reinforcement learning (RL) tasks have been useful to\ndrive progress in the field, they are in many ways poor substitutes for\nlearning with real-world data. By testing increasingly complex RL algorithms on\nlow-complexity simulation environments, we often end up with brittle RL\npolicies that generalize poorly beyond the very specific domain. To combat\nthis, we propose three new families of benchmark RL domains that contain some\nof the complexity of the natural world, while still supporting fast and\nextensive data acquisition. The proposed domains also permit a characterization\nof generalization through fair train/test separation, and easy comparison and\nreplication of results. Through this work, we challenge the RL research\ncommunity to develop more robust algorithms that meet high standards of\nevaluation.","url_abs":"http://arxiv.org/abs/1811.06032v1","url_pdf":"http://arxiv.org/pdf/1811.06032v1.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":"natural-environment-benchmarks-for","repo_url":"https://github.com/bchidamb/RL-Image-Classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"natural-environment-benchmarks-for","repo_url":"https://github.com/manhdung20112000/RL-Image-Classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1811.06032","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}