{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:11:29Z","timestamp":1765519889267,"version":"3.48.0"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100016311","name":"Arm","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016311","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246149","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"2337-2344","source":"Crossref","is-referenced-by-count":0,"title":["Confidence-Controlled Exploration: Efficient Sparse-Reward Policy Learning for Robot Navigation"],"prefix":"10.1109","author":[{"given":"Bhrij","family":"Patel","sequence":"first","affiliation":[{"name":"University of Maryland,Department of Computer Science,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kasun","family":"Weerakoon","sequence":"additional","affiliation":[{"name":"University of Maryland,Department of Computer Science,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wesley A.","family":"Suttle","sequence":"additional","affiliation":[{"name":"U.S. Army Research Laboratory,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alec","family":"Koppel","sequence":"additional","affiliation":[{"name":"JP Morgan AI Research,New York,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian M.","family":"Sadler","sequence":"additional","affiliation":[{"name":"University of Texas at Austin,Austin,TX,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyi","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Maryland,Department of Computer Science,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dinesh","family":"Manocha","sequence":"additional","affiliation":[{"name":"University of Maryland,Department of Computer Science,College Park,MD,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amrit Singh","family":"Bedi","sequence":"additional","affiliation":[{"name":"University of Central Florida,Department of Computer Science,Orlando,FL,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.17694\/bajece.781162"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9407.001.0001"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-6670(17)41063-9"},{"volume-title":"Reinforcement learning: An introduction","year":"2018","author":"Sutton","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.26599\/TST.2021.9010012"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"article-title":"Reinforcement learning with sparse rewards using guidance from offline demonstration","volume-title":"International Conference on Learning Representations","author":"Rengarajan","key":"ref7"},{"article-title":"Dealing with sparse rewards in reinforcement learning","year":"2019","author":"Hare","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2020.2973193"},{"article-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","year":"2017","author":"Vecerik","key":"ref10"},{"issue":"39","key":"ref11","first-page":"1","article-title":"On the sample complexity and metastability of heavy-tailed policy search in continuous control","volume":"25","author":"Bedi","year":"2024","journal-title":"Journal of Machine Learning Research"},{"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","key":"ref12"},{"article-title":"On reward shaping for mobile robot navigation: A reinforcement learning and slam based approach","year":"2020","author":"Botteghi","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50030-1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2899918"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161186"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1090\/mbk\/107"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5968"},{"volume-title":"The complexity of robot motion planning","year":"1988","author":"Canny","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511546877"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-022-10039-8"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812238"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11645"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3034524"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.3139\/9783446466081","volume-title":"Deep reinforcement learning in action","author":"Zai","year":"2020"},{"key":"ref27","first-page":"10444","article-title":"Copilot: Collaborative planning and reinforcement learning on sub-task curriculum","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Ao","year":"2021"},{"key":"ref28","article-title":"Vime: Variational information maximizing exploration","volume":"29","author":"Houthooft","year":"2016","journal-title":"Advances in neural information processing systems"},{"article-title":"HTRON: Efficient outdoor navigation with sparse rewards via heavy tailed adaptive reinforce algorithm","volume-title":"6th Annual Conference on Robot Learning","author":"Weerakoon","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9130-2"},{"article-title":"Adaptive rollout length for model-based rl using model-free deep rl","year":"2022","author":"Bhatia","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561842"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543636"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.19026\/rjaset.8.1117"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1115\/DETC2019-97887"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560822"},{"key":"ref37","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"Sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"article-title":"Beyond exponentially fast mixing in average-reward reinforcement learning via multi-level monte carlo actor-critic","volume-title":"International Conference on Machine Learning","author":"Suttle","key":"ref38"},{"article-title":"Adapting to mixing time in stochastic optimization with Markovian data","volume-title":"Proceedings of the 39th International Conference on Machine Learning","author":"Dorfman","key":"ref39"},{"key":"ref40","article-title":"Continual learning in environments with polynomial mixing times","author":"Riemer","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref41","article-title":"Mixing time estimation in reversible markov chains from a single sample path","author":"Hsu","year":"2015","journal-title":"CoRR"},{"article-title":"Mixing time estimation in ergodic markov chains from a single trajectory with contraction methods","volume-title":"Proceedings of the 31st International Conference on Algorithmic Learning Theory","author":"Wolfer","key":"ref42"},{"key":"ref43","first-page":"974","article-title":"Active exploration in markov decision processes","volume-title":"The 22nd International Conference on Artificial Intelligence and Statistics","author":"Tarbouriech"},{"article-title":"Maximum entropy rl (provably) solves some robust rl problems","volume-title":"International Conference on Learning Representations","author":"Eysenbach","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3011912"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1561\/0400000003"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246149.pdf?arnumber=11246149","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:10:04Z","timestamp":1765519804000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246149\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246149","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}