{"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/optimizing-the-cvar-via-sampling","title":"Optimizing the CVaR via Sampling","arxiv_id":"1404.3862","date":"2014-04-15","proceeding":null,"authors":["Aviv Tamar","Yonatan Glassner","Shie Mannor"],"abstract":"Conditional Value at Risk (CVaR) is a prominent risk measure that is being\nused extensively in various domains. We develop a new formula for the gradient\nof the CVaR in the form of a conditional expectation. Based on this formula, we\npropose a novel sampling-based estimator for the CVaR gradient, in the spirit\nof the likelihood-ratio method. We analyze the bias of the estimator, and prove\nthe convergence of a corresponding stochastic gradient descent algorithm to a\nlocal CVaR optimum. Our method allows to consider CVaR optimization in new\ndomains. As an example, we consider a reinforcement learning application, and\nlearn a risk-sensitive controller for the game of Tetris.","url_abs":"http://arxiv.org/abs/1404.3862v4","url_pdf":"http://arxiv.org/pdf/1404.3862v4.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":"optimizing-the-cvar-via-sampling","repo_url":"https://github.com/ido90/CeSoR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"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":{"atlas_url":"https://app.syntology.ai/?focus=1404.3862","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}