{"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/the-advantage-of-doubling-a-deep","title":"The Advantage of Doubling: A Deep Reinforcement Learning Approach to Studying the Double Team in the NBA","arxiv_id":"1803.02940","date":"2018-03-08","proceeding":null,"authors":["Jiaxuan Wang","Ian Fox","Jonathan Skaza","Nick Linck","Satinder Singh","Jenna Wiens"],"abstract":"During the 2017 NBA playoffs, Celtics coach Brad Stevens was faced with a\ndifficult decision when defending against the Cavaliers: \"Do you double and\nrisk giving up easy shots, or stay at home and do the best you can?\" It's a\ntough call, but finding a good defensive strategy that effectively incorporates\ndoubling can make all the difference in the NBA. In this paper, we analyze\ndouble teaming in the NBA, quantifying the trade-off between risk and reward.\nUsing player trajectory data pertaining to over 643,000 possessions, we\nidentified when the ball handler was double teamed. Given these data and the\ncorresponding outcome (i.e., was the defense successful), we used deep\nreinforcement learning to estimate the quality of the defensive actions. We\npresent qualitative and quantitative results summarizing our learned defensive\nstrategy for defending. We show that our policy value estimates are predictive\nof points per possession and win percentage. Overall, the proposed framework\nrepresents a step toward a more comprehensive understanding of defensive\nstrategies in the NBA.","url_abs":"http://arxiv.org/abs/1803.02940v1","url_pdf":"http://arxiv.org/pdf/1803.02940v1.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":"the-advantage-of-doubling-a-deep","repo_url":"https://github.com/igfox/AdvantageOfDoubling","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.02940","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}