{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:17:36Z","timestamp":1740100656574,"version":"3.37.3"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,3,9]],"date-time":"2022-03-09T00:00:00Z","timestamp":1646784000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,3,9]],"date-time":"2022-03-09T00:00:00Z","timestamp":1646784000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006754","name":"US Army Research Laboratory (ARL)","doi-asserted-by":"publisher","award":["W911NF-22-2-0003"],"award-info":[{"award-number":["W911NF-22-2-0003"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,3,9]]},"DOI":"10.1109\/ciss53076.2022.9751163","type":"proceedings-article","created":{"date-parts":[[2022,4,14]],"date-time":"2022-04-14T19:40:07Z","timestamp":1649965207000},"page":"281-286","source":"Crossref","is-referenced-by-count":0,"title":["Policy Gradient for Ratio Optimization: A Case Study"],"prefix":"10.1109","author":[{"given":"Wesley A.","family":"Suttle","sequence":"first","affiliation":[{"name":"Stony Brook University,Applied Mathematics and Statistics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alec","family":"Koppel","sequence":"additional","affiliation":[{"name":"Supply Chain Optimization Technologies, Amazon,Optimal Sourcing Systems"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ji","family":"Liu","sequence":"additional","affiliation":[{"name":"Stony Brook University,Electrical and Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2005.846520"},{"key":"ref11","first-page":"9989","article-title":"Reinforcement learning for cost-aware Markov decision processes","author":"suttle","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref12","first-page":"77","article-title":"Portfolio selection","volume":"7","author":"markowitz","year":"1952","journal-title":"The Journal of Finance"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3905\/joi.3.3.11"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1086\/294846"},{"key":"ref15","first-page":"40","article-title":"Calmar ratio: A smoother tool","volume":"20","author":"young","year":"1991","journal-title":"Futures"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3905\/joi.3.3.59"},{"key":"ref17","first-page":"59","article-title":"A universal performance measure","volume":"6","author":"keating","year":"2002","journal-title":"Journal of Performance Measurement"},{"key":"ref18","first-page":"279","article-title":"Reinforcement learning for trading systems and portfolios","author":"moody","year":"0","journal-title":"KDD"},{"key":"ref19","first-page":"936","article-title":"Enhancing Q-learning for optimal asset allocation","author":"neuneier","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/BF02745577"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref6","first-page":"4358","article-title":"Improving sample complexity bounds for (natural) actor-critic algorithms","volume":"33","author":"xu","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref5","article-title":"On the sample complexity of actor-critic method for reinforcement learning with function approximation","author":"kumar","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9482783"},{"key":"ref7","first-page":"4572","article-title":"Variational policy gradient method for reinforcement learning with general utilities","volume":"33","author":"zhang","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref2","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"99","author":"sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"On the convergence and sample efficiency of variance-reduced policy gradient method","author":"zhang","year":"2021","journal-title":"ArXiv Preprint"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/72.935097"},{"journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming","year":"2014","author":"puterman","key":"ref22"},{"key":"ref21","article-title":"A deep reinforcement learning framework for the financial portfolio management problem","author":"jiang","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719437"},{"journal-title":"Actor-critic algorithms","year":"2002","author":"konda","key":"ref23"},{"journal-title":"Stochastic Approximation A Dynamical Systems View-point","year":"2008","author":"borkar","key":"ref26"},{"journal-title":"Stochastic Approximation and Recursive Algorithms and Applications","year":"2003","author":"kushner","key":"ref25"}],"event":{"name":"2022 56th Annual Conference on Information Sciences and Systems (CISS)","start":{"date-parts":[[2022,3,9]]},"location":"Princeton, NJ, USA","end":{"date-parts":[[2022,3,11]]}},"container-title":["2022 56th Annual Conference on Information Sciences and Systems (CISS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9751119\/9751149\/09751163.pdf?arnumber=9751163","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,15]],"date-time":"2022-06-15T20:15:15Z","timestamp":1655324115000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9751163\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,9]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/ciss53076.2022.9751163","relation":{},"subject":[],"published":{"date-parts":[[2022,3,9]]}}}