{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:35:34Z","timestamp":1740101734070,"version":"3.37.3"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T00:00:00Z","timestamp":1679443200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T00:00:00Z","timestamp":1679443200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006754","name":"U.S. Army Research Laboratory","doi-asserted-by":"publisher","award":["W911NF-21-2-0127,W911NF-22-2-0003"],"award-info":[{"award-number":["W911NF-21-2-0127,W911NF-22-2-0003"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2230101"],"award-info":[{"award-number":["2230101"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,3,22]]},"DOI":"10.1109\/ciss56502.2023.10089655","type":"proceedings-article","created":{"date-parts":[[2023,4,10]],"date-time":"2023-04-10T18:58:36Z","timestamp":1681153116000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Information-Directed Policy Search in Sparse-Reward Settings via the Occupancy Information Ratio"],"prefix":"10.1109","author":[{"given":"Wesley A.","family":"Suttle","sequence":"first","affiliation":[{"name":"U.s. Army Research Laboratory,Adelphi,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alec","family":"Koppel","sequence":"additional","affiliation":[{"name":"J.P’ Morgan AI Research,New York,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ji","family":"Liu","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering Stony Brook University,Stony Brook,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"journal-title":"Prox-imal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref4"},{"key":"ref5","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International Conference on Machine Learning","author":"Haarnoja","year":"2018"},{"key":"ref6","first-page":"1583","article-title":"Learning to optimize via information-directed sampling","volume":"27","author":"Russo","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1561\/9781638282556"},{"key":"ref8","first-page":"2681","article-title":"Provably efficient maximum entropy exploration","volume-title":"International Conference on Machine Learning","author":"Hazan","year":"2019"},{"journal-title":"Efficient exploration via state marginal matching","year":"2019","author":"Lee","key":"ref9"},{"key":"ref10","first-page":"4572","article-title":"Variational policy gradient method for reinforcement learning with general utilities","volume":"33","author":"Zhang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximtion","volume":"99","author":"Sutton","year":"1999","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","article-title":"Global optimality guarantees for policy gradient methods","author":"Bhandari","year":"2019","journal-title":"arXiv preprint"},{"key":"ref13","first-page":"64","article-title":"Optimality and approximation with policy gradient methods in Markov decision processes","volume-title":"Conference on Learning Theory","author":"Agarwal","year":"2020"},{"key":"ref14","first-page":"6820","article-title":"On the global convergence rates of softmax policy gradient methods","volume-title":"International Conference on Machine Learning","author":"Mei","year":"2020"},{"key":"ref15","article-title":"On the sample complexity and metastability of heavy-tailed policy search in continuous control","author":"Bedi","year":"2021","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","author":"Vecerik","year":"2017","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.073"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref19","first-page":"4344","article-title":"Learning by playing solving sparse reward tasks from scratch","volume-title":"International Conference on Machine Learning. PMLR","author":"Riedmiller","year":"2018"},{"key":"ref20","first-page":"11920","article-title":"Reinforcement learning with prototypical representations","volume-title":"International Conference on Machine Learning. PMLR","author":"Yarats","year":"2021"},{"key":"ref21","first-page":"18459","article-title":"Behavior from the void: Unsupervised active pre-training","volume":"34","author":"Liu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"Actor-critic algorithms","year":"2002","author":"Konda","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1137\/19M1288012"}],"event":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","start":{"date-parts":[[2023,3,22]]},"location":"Baltimore, MD, USA","end":{"date-parts":[[2023,3,24]]}},"container-title":["2023 57th Annual Conference on Information Sciences and Systems (CISS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10089615\/10089616\/10089655.pdf?arnumber=10089655","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T11:09:28Z","timestamp":1709464168000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10089655\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,22]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/ciss56502.2023.10089655","relation":{},"subject":[],"published":{"date-parts":[[2023,3,22]]}}}