default search action
BibTeX records: Prashanth L. A.
@article{DBLP:journals/automatica/MondalAB24, author = {Akash Mondal and Prashanth L. A. and Shalabh Bhatnagar}, title = {Truncated Cauchy random perturbations for smoothed functional-based stochastic optimization}, journal = {Autom.}, volume = {162}, pages = {111528}, year = {2024}, url = {https://doi.org/10.1016/j.automatica.2024.111528}, doi = {10.1016/J.AUTOMATICA.2024.111528}, timestamp = {Fri, 26 Jul 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/automatica/MondalAB24.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aistats/ManiyarAMB24, author = {Mizhaan Prajit Maniyar and Prashanth L. A. and Akash Mondal and Shalabh Bhatnagar}, editor = {Sanjoy Dasgupta and Stephan Mandt and Yingzhen Li}, title = {A Cubic-regularized Policy Newton Algorithm for Reinforcement Learning}, booktitle = {International Conference on Artificial Intelligence and Statistics, 2-4 May 2024, Palau de Congressos, Valencia, Spain}, series = {Proceedings of Machine Learning Research}, volume = {238}, pages = {4708--4716}, publisher = {{PMLR}}, year = {2024}, url = {https://proceedings.mlr.press/v238/maniyar24a.html}, timestamp = {Mon, 13 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/aistats/ManiyarAMB24.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/AgrawalAM24, author = {Shubhada Agrawal and Prashanth L. A. and Siva Theja Maguluri}, title = {Policy Evaluation for Variance in Average Reward Reinforcement Learning}, booktitle = {Forty-first International Conference on Machine Learning, {ICML} 2024, Vienna, Austria, July 21-27, 2024}, publisher = {OpenReview.net}, year = {2024}, url = {https://openreview.net/forum?id=bID9PiBFpT}, timestamp = {Mon, 02 Sep 2024 16:45:29 +0200}, biburl = {https://dblp.org/rec/conf/icml/AgrawalAM24.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/ThoppeAB24, author = {Gugan Thoppe and Prashanth L. A. and Sanjay P. Bhat}, title = {Risk Estimation in a Markov Cost Process: Lower and Upper Bounds}, booktitle = {Forty-first International Conference on Machine Learning, {ICML} 2024, Vienna, Austria, July 21-27, 2024}, publisher = {OpenReview.net}, year = {2024}, url = {https://openreview.net/forum?id=7xzhKEPfBo}, timestamp = {Mon, 02 Sep 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icml/ThoppeAB24.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2405-20933, author = {Ayon Ghosh and Prashanth L. A. and Krishna P. Jagannathan}, title = {Concentration Bounds for Optimized Certainty Equivalent Risk Estimation}, journal = {CoRR}, volume = {abs/2405.20933}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2405.20933}, doi = {10.48550/ARXIV.2405.20933}, eprinttype = {arXiv}, eprint = {2405.20933}, timestamp = {Mon, 24 Jun 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2405-20933.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2406-07892, author = {Tejaram Sangadi and Prashanth L. A. and Krishna P. Jagannathan}, title = {Finite Time Analysis of Temporal Difference Learning for Mean-Variance in a Discounted {MDP}}, journal = {CoRR}, volume = {abs/2406.07892}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2406.07892}, doi = {10.48550/ARXIV.2406.07892}, eprinttype = {arXiv}, eprint = {2406.07892}, timestamp = {Mon, 08 Jul 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2406-07892.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tac/BhavsarA23, author = {Nirav Bhavsar and Prashanth L. A.}, title = {Nonasymptotic Bounds for Stochastic Optimization With Biased Noisy Gradient Oracles}, journal = {{IEEE} Trans. Autom. Control.}, volume = {68}, number = {3}, pages = {1628--1641}, year = {2023}, url = {https://doi.org/10.1109/TAC.2022.3159748}, doi = {10.1109/TAC.2022.3159748}, timestamp = {Sat, 11 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/tac/BhavsarA23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aistats/PatilANP23, author = {Gandharv Patil and Prashanth L. A. and Dheeraj Nagaraj and Doina Precup}, editor = {Francisco J. R. Ruiz and Jennifer G. Dy and Jan{-}Willem van de Meent}, title = {Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation}, booktitle = {International Conference on Artificial Intelligence and Statistics, 25-27 April 2023, Palau de Congressos, Valencia, Spain}, series = {Proceedings of Machine Learning Research}, volume = {206}, pages = {5438--5448}, publisher = {{PMLR}}, year = {2023}, url = {https://proceedings.mlr.press/v206/patil23a.html}, timestamp = {Mon, 19 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/aistats/PatilANP23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ciss/BhatnagarA23, author = {Shalabh Bhatnagar and Prashanth L. A.}, title = {Generalized Simultaneous Perturbation Stochastic Approximation with Reduced Estimator Bias}, booktitle = {57th Annual Conference on Information Sciences and Systems, {CISS} 2023, Baltimore, MD, USA, March 22-24, 2023}, pages = {1--6}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/CISS56502.2023.10089720}, doi = {10.1109/CISS56502.2023.10089720}, timestamp = {Sat, 22 Apr 2023 16:25:53 +0200}, biburl = {https://dblp.org/rec/conf/ciss/BhatnagarA23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/uai/VijayanA23, author = {Nithia Vijayan and Prashanth L. A.}, editor = {Robin J. Evans and Ilya Shpitser}, title = {A policy gradient approach for optimization of smooth risk measures}, booktitle = {Uncertainty in Artificial Intelligence, {UAI} 2023, July 31 - 4 August 2023, Pittsburgh, PA, {USA}}, series = {Proceedings of Machine Learning Research}, volume = {216}, pages = {2168--2178}, publisher = {{PMLR}}, year = {2023}, url = {https://proceedings.mlr.press/v216/vijayan23a.html}, timestamp = {Mon, 28 Aug 2023 17:23:08 +0200}, biburl = {https://dblp.org/rec/conf/uai/VijayanA23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2304-10951, author = {Mizhaan Prajit Maniyar and Akash Mondal and Prashanth L. A. and Shalabh Bhatnagar}, title = {A Cubic-regularized Policy Newton Algorithm for Reinforcement Learning}, journal = {CoRR}, volume = {abs/2304.10951}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2304.10951}, doi = {10.48550/ARXIV.2304.10951}, eprinttype = {arXiv}, eprint = {2304.10951}, timestamp = {Tue, 02 May 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2304-10951.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2310-11389, author = {Sanjay Bhat and Prashanth L. A. and Gugan Thoppe}, title = {VaR{\textbackslash} and CVaR Estimation in a Markov Cost Process: Lower and Upper Bounds}, journal = {CoRR}, volume = {abs/2310.11389}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2310.11389}, doi = {10.48550/ARXIV.2310.11389}, eprinttype = {arXiv}, eprint = {2310.11389}, timestamp = {Thu, 26 Oct 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2310-11389.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2310-18743, author = {Sumedh Gupte and Prashanth L. A. and Sanjay P. Bhat}, title = {Optimization of utility-based shortfall risk: {A} non-asymptotic viewpoint}, journal = {CoRR}, volume = {abs/2310.18743}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2310.18743}, doi = {10.48550/ARXIV.2310.18743}, eprinttype = {arXiv}, eprint = {2310.18743}, timestamp = {Thu, 02 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2310-18743.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ftml/A022, author = {Prashanth L. A. and Michael C. Fu}, title = {Risk-Sensitive Reinforcement Learning via Policy Gradient Search}, journal = {Found. Trends Mach. Learn.}, volume = {15}, number = {5}, pages = {537--693}, year = {2022}, url = {https://doi.org/10.1561/2200000091}, doi = {10.1561/2200000091}, timestamp = {Thu, 14 Jul 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ftml/A022.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jmlr/AB22, author = {Prashanth L. A. and Sanjay P. Bhat}, title = {A Wasserstein Distance Approach for Concentration of Empirical Risk Estimates}, journal = {J. Mach. Learn. Res.}, volume = {23}, pages = {238:1--238:61}, year = {2022}, url = {https://jmlr.org/papers/v23/20-965.html}, timestamp = {Wed, 11 Sep 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/jmlr/AB22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcai/TanAJ22, author = {Vincent Y. F. Tan and Prashanth L. A. and Krishna P. Jagannathan}, editor = {Luc De Raedt}, title = {A Survey of Risk-Aware Multi-Armed Bandits}, booktitle = {Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, {IJCAI} 2022, Vienna, Austria, 23-29 July 2022}, pages = {5623--5629}, publisher = {ijcai.org}, year = {2022}, url = {https://doi.org/10.24963/ijcai.2022/784}, doi = {10.24963/IJCAI.2022/784}, timestamp = {Wed, 27 Jul 2022 16:43:00 +0200}, biburl = {https://dblp.org/rec/conf/ijcai/TanAJ22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2202-11046, author = {Nithia Vijayan and Prashanth L. A.}, title = {Approximate gradient ascent methods for distortion risk measures}, journal = {CoRR}, volume = {abs/2202.11046}, year = {2022}, url = {https://arxiv.org/abs/2202.11046}, eprinttype = {arXiv}, eprint = {2202.11046}, timestamp = {Wed, 02 Mar 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2202-11046.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-16810, author = {Dipayan Sen and Prashanth L. A. and Aditya Gopalan}, title = {Adaptive Estimation of Random Vectors with Bandit Feedback}, journal = {CoRR}, volume = {abs/2203.16810}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.16810}, doi = {10.48550/ARXIV.2203.16810}, eprinttype = {arXiv}, eprint = {2203.16810}, timestamp = {Mon, 04 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-16810.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2205-05843, author = {Vincent Y. F. Tan and Prashanth L. A. and Krishna P. Jagannathan}, title = {A Survey of Risk-Aware Multi-Armed Bandits}, journal = {CoRR}, volume = {abs/2205.05843}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2205.05843}, doi = {10.48550/ARXIV.2205.05843}, eprinttype = {arXiv}, eprint = {2205.05843}, timestamp = {Wed, 18 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2205-05843.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2208-00290, author = {Akash Mondal and Prashanth L. A. and Shalabh Bhatnagar}, title = {A Gradient Smoothed Functional Algorithm with Truncated Cauchy Random Perturbations for Stochastic Optimization}, journal = {CoRR}, volume = {abs/2208.00290}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2208.00290}, doi = {10.48550/ARXIV.2208.00290}, eprinttype = {arXiv}, eprint = {2208.00290}, timestamp = {Wed, 10 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2208-00290.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2210-05918, author = {Gandharv Patil and Prashanth L. A. and Dheeraj Nagaraj and Doina Precup}, title = {Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation}, journal = {CoRR}, volume = {abs/2210.05918}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2210.05918}, doi = {10.48550/ARXIV.2210.05918}, eprinttype = {arXiv}, eprint = {2210.05918}, timestamp = {Tue, 18 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2210-05918.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2212-10477, author = {Shalabh Bhatnagar and Prashanth L. A.}, title = {Generalized Simultaneous Perturbation Stochastic Approximation with Reduced Estimator Bias}, journal = {CoRR}, volume = {abs/2212.10477}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2212.10477}, doi = {10.48550/ARXIV.2212.10477}, eprinttype = {arXiv}, eprint = {2212.10477}, timestamp = {Wed, 04 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2212-10477.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ml/AKM21, author = {Prashanth L. A. and Nathaniel Korda and R{\'{e}}mi Munos}, title = {Concentration bounds for temporal difference learning with linear function approximation: the case of batch data and uniform sampling}, journal = {Mach. Learn.}, volume = {110}, number = {3}, pages = {559--618}, year = {2021}, url = {https://doi.org/10.1007/s10994-020-05912-5}, doi = {10.1007/S10994-020-05912-5}, timestamp = {Wed, 07 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ml/AKM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/scl/VijayanA21, author = {Nithia Vijayan and Prashanth L. A.}, title = {Smoothed functional-based gradient algorithms for off-policy reinforcement learning: {A} non-asymptotic viewpoint}, journal = {Syst. Control. Lett.}, volume = {155}, pages = {104988}, year = {2021}, url = {https://doi.org/10.1016/j.sysconle.2021.104988}, doi = {10.1016/J.SYSCONLE.2021.104988}, timestamp = {Mon, 28 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/scl/VijayanA21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaai/PandeyAB21, author = {Ajay Kumar Pandey and Prashanth L. A. and Sanjay P. Bhat}, title = {Estimation of Spectral Risk Measures}, booktitle = {Thirty-Fifth {AAAI} Conference on Artificial Intelligence, {AAAI} 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, {IAAI} 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2021, Virtual Event, February 2-9, 2021}, pages = {12166--12173}, publisher = {{AAAI} Press}, year = {2021}, url = {https://doi.org/10.1609/aaai.v35i13.17444}, doi = {10.1609/AAAI.V35I13.17444}, timestamp = {Mon, 04 Sep 2023 12:29:24 +0200}, biburl = {https://dblp.org/rec/conf/aaai/PandeyAB21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2101-02137, author = {Nithia Vijayan and Prashanth L. A.}, title = {Smoothed functional-based gradient algorithms for off-policy reinforcement learning}, journal = {CoRR}, volume = {abs/2101.02137}, year = {2021}, url = {https://arxiv.org/abs/2101.02137}, eprinttype = {arXiv}, eprint = {2101.02137}, timestamp = {Tue, 30 Mar 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2101-02137.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2107-04422, author = {Nithia Vijayan and Prashanth L. A.}, title = {Likelihood ratio-based policy gradient methods for distorted risk measures: {A} non-asymptotic analysis}, journal = {CoRR}, volume = {abs/2107.04422}, year = {2021}, url = {https://arxiv.org/abs/2107.04422}, eprinttype = {arXiv}, eprint = {2107.04422}, timestamp = {Tue, 20 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2107-04422.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2111-08805, author = {Arvind S. Menon and Prashanth L. A. and Krishna P. Jagannathan}, title = {Online Estimation and Optimization of Utility-Based Shortfall Risk}, journal = {CoRR}, volume = {abs/2111.08805}, year = {2021}, url = {https://arxiv.org/abs/2111.08805}, eprinttype = {arXiv}, eprint = {2111.08805}, timestamp = {Mon, 22 Nov 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2111-08805.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tac/ABBFM20, author = {Prashanth L. A. and Shalabh Bhatnagar and Nirav Bhavsar and Michael C. Fu and Steven I. Marcus}, title = {Random Directions Stochastic Approximation With Deterministic Perturbations}, journal = {{IEEE} Trans. Autom. Control.}, volume = {65}, number = {6}, pages = {2450--2465}, year = {2020}, url = {https://doi.org/10.1109/TAC.2019.2930821}, doi = {10.1109/TAC.2019.2930821}, timestamp = {Tue, 16 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tac/ABBFM20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/AJK20, author = {Prashanth L. A. and Krishna P. Jagannathan and Ravi Kumar Kolla}, title = {Concentration bounds for CVaR estimation: The cases of light-tailed and heavy-tailed distributions}, booktitle = {Proceedings of the 37th International Conference on Machine Learning, {ICML} 2020, 13-18 July 2020, Virtual Event}, series = {Proceedings of Machine Learning Research}, volume = {119}, pages = {5577--5586}, publisher = {{PMLR}}, year = {2020}, url = {http://proceedings.mlr.press/v119/l-a-20a.html}, timestamp = {Tue, 15 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icml/AJK20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2002-11440, author = {Nirav Bhavsar and Prashanth L. A.}, title = {Non-Asymptotic Bounds for Zeroth-Order Stochastic Optimization}, journal = {CoRR}, volume = {abs/2002.11440}, year = {2020}, url = {https://arxiv.org/abs/2002.11440}, eprinttype = {arXiv}, eprint = {2002.11440}, timestamp = {Tue, 03 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2002-11440.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/orl/KollaABJ19, author = {Ravi Kumar Kolla and Prashanth L. A. and Sanjay P. Bhat and Krishna P. Jagannathan}, title = {Concentration bounds for empirical conditional value-at-risk: The unbounded case}, journal = {Oper. Res. Lett.}, volume = {47}, number = {1}, pages = {16--20}, year = {2019}, url = {https://doi.org/10.1016/j.orl.2018.11.005}, doi = {10.1016/J.ORL.2018.11.005}, timestamp = {Wed, 13 Feb 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/orl/KollaABJ19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/BodaA19, author = {Vinay Praneeth Boda and Prashanth L. A.}, editor = {Kamalika Chaudhuri and Ruslan Salakhutdinov}, title = {Correlated bandits or: How to minimize mean-squared error online}, booktitle = {Proceedings of the 36th International Conference on Machine Learning, {ICML} 2019, 9-15 June 2019, Long Beach, California, {USA}}, series = {Proceedings of Machine Learning Research}, volume = {97}, pages = {686--694}, publisher = {{PMLR}}, year = {2019}, url = {http://proceedings.mlr.press/v97/boda19a.html}, timestamp = {Tue, 11 Jun 2019 15:37:38 +0200}, biburl = {https://dblp.org/rec/conf/icml/BodaA19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/BhatA19, author = {Sanjay P. Bhat and Prashanth L. A.}, editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alch{\'{e}}{-}Buc and Emily B. Fox and Roman Garnett}, title = {Concentration of risk measures: {A} Wasserstein distance approach}, booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada}, pages = {11739--11748}, year = {2019}, url = {https://proceedings.neurips.cc/paper/2019/hash/091bc5440296cc0e41dd60ce22fbaf88-Abstract.html}, timestamp = {Mon, 16 May 2022 15:41:51 +0200}, biburl = {https://dblp.org/rec/conf/nips/BhatA19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1901-00997, author = {Ravi Kumar Kolla and Prashanth L. A. and Krishna P. Jagannathan}, title = {Risk-aware Multi-armed Bandits Using Conditional Value-at-Risk}, journal = {CoRR}, volume = {abs/1901.00997}, year = {2019}, url = {http://arxiv.org/abs/1901.00997}, eprinttype = {arXiv}, eprint = {1901.00997}, timestamp = {Thu, 31 Jan 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1901-00997.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1902-02953, author = {Vinay Praneeth Boda and Prashanth L. A.}, title = {Correlated bandits or: How to minimize mean-squared error online}, journal = {CoRR}, volume = {abs/1902.02953}, year = {2019}, url = {http://arxiv.org/abs/1902.02953}, eprinttype = {arXiv}, eprint = {1902.02953}, timestamp = {Tue, 21 May 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1902-02953.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1902-10709, author = {Sanjay P. Bhat and Prashanth L. A.}, title = {Improved Concentration Bounds for Conditional Value-at-Risk and Cumulative Prospect Theory using Wasserstein distance}, journal = {CoRR}, volume = {abs/1902.10709}, year = {2019}, url = {http://arxiv.org/abs/1902.10709}, eprinttype = {arXiv}, eprint = {1902.10709}, timestamp = {Tue, 21 May 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1902-10709.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1912-10398, author = {Ajay Kumar Pandey and Prashanth L. A. and Sanjay P. Bhat}, title = {Estimation of Spectral Risk Measures}, journal = {CoRR}, volume = {abs/1912.10398}, year = {2019}, url = {http://arxiv.org/abs/1912.10398}, eprinttype = {arXiv}, eprint = {1912.10398}, timestamp = {Fri, 03 Jan 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1912-10398.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tac/JieAFMS18, author = {Cheng Jie and Prashanth L. A. and Michael C. Fu and Steven I. Marcus and Csaba Szepesv{\'{a}}ri}, title = {Stochastic Optimization in a Cumulative Prospect Theory Framework}, journal = {{IEEE} Trans. Autom. Control.}, volume = {63}, number = {9}, pages = {2867--2882}, year = {2018}, url = {https://doi.org/10.1109/TAC.2018.2822658}, doi = {10.1109/TAC.2018.2822658}, timestamp = {Wed, 20 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tac/JieAFMS18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1808-01739, author = {Ravi Kumar Kolla and Prashanth L. A. and Sanjay P. Bhat and Krishna P. Jagannathan}, title = {Concentration bounds for empirical conditional value-at-risk: The unbounded case}, journal = {CoRR}, volume = {abs/1808.01739}, year = {2018}, url = {http://arxiv.org/abs/1808.01739}, eprinttype = {arXiv}, eprint = {1808.01739}, timestamp = {Sun, 02 Sep 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1808-01739.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1808-02871, author = {Prashanth L. A. and Shalabh Bhatnagar and Nirav Bhavsar and Michael C. Fu and Steven I. Marcus}, title = {Random directions stochastic approximation with deterministic perturbations}, journal = {CoRR}, volume = {abs/1808.02871}, year = {2018}, url = {http://arxiv.org/abs/1808.02871}, eprinttype = {arXiv}, eprint = {1808.02871}, timestamp = {Wed, 20 Nov 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1808-02871.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1810-09126, author = {Prashanth L. A. and Michael C. Fu}, title = {Risk-Sensitive Reinforcement Learning: {A} Constrained Optimization Viewpoint}, journal = {CoRR}, volume = {abs/1810.09126}, year = {2018}, url = {http://arxiv.org/abs/1810.09126}, eprinttype = {arXiv}, eprint = {1810.09126}, timestamp = {Wed, 20 Nov 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1810-09126.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tac/ABFM17, author = {Prashanth L. A. and Shalabh Bhatnagar and Michael C. Fu and Steven I. Marcus}, title = {Adaptive System Optimization Using Random Directions Stochastic Approximation}, journal = {{IEEE} Trans. Autom. Control.}, volume = {62}, number = {5}, pages = {2223--2238}, year = {2017}, url = {https://doi.org/10.1109/TAC.2016.2600643}, doi = {10.1109/TAC.2016.2600643}, timestamp = {Sat, 09 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tac/ABFM17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaai/GopalanAFM17, author = {Aditya Gopalan and Prashanth L. A. and Michael C. Fu and Steven I. Marcus}, editor = {Satinder Singh and Shaul Markovitch}, title = {Weighted Bandits or: How Bandits Learn Distorted Values That Are Not Expected}, booktitle = {Proceedings of the Thirty-First {AAAI} Conference on Artificial Intelligence, February 4-9, 2017, San Francisco, California, {USA}}, pages = {1941--1947}, publisher = {{AAAI} Press}, year = {2017}, url = {https://doi.org/10.1609/aaai.v31i1.10922}, doi = {10.1609/AAAI.V31I1.10922}, timestamp = {Mon, 04 Sep 2023 14:40:32 +0200}, biburl = {https://dblp.org/rec/conf/aaai/GopalanAFM17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ml/AG16, author = {Prashanth L. A. and Mohammad Ghavamzadeh}, title = {Variance-constrained actor-critic algorithms for discounted and average reward MDPs}, journal = {Mach. Learn.}, volume = {105}, number = {3}, pages = {367--417}, year = {2016}, url = {https://doi.org/10.1007/s10994-016-5569-5}, doi = {10.1007/S10994-016-5569-5}, timestamp = {Mon, 02 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ml/AG16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/scl/APBC16, author = {Prashanth L. A. and H. L. Prasad and Shalabh Bhatnagar and Prakash Chandra}, title = {A constrained optimization perspective on actor-critic algorithms and application to network routing}, journal = {Syst. Control. Lett.}, volume = {92}, pages = {46--51}, year = {2016}, url = {https://doi.org/10.1016/j.sysconle.2016.02.020}, doi = {10.1016/J.SYSCONLE.2016.02.020}, timestamp = {Sat, 09 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/scl/APBC16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aistats/HuAGS16, author = {Xiaowei Hu and Prashanth L. A. and Andr{\'{a}}s Gy{\"{o}}rgy and Csaba Szepesv{\'{a}}ri}, editor = {Arthur Gretton and Christian C. Robert}, title = {(Bandit) Convex Optimization with Biased Noisy Gradient Oracles}, booktitle = {Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, {AISTATS} 2016, Cadiz, Spain, May 9-11, 2016}, series = {{JMLR} Workshop and Conference Proceedings}, volume = {51}, pages = {819--828}, publisher = {JMLR.org}, year = {2016}, url = {http://proceedings.mlr.press/v51/hu16b.html}, timestamp = {Tue, 15 Feb 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/aistats/HuAGS16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cdc/ReddyAB16, author = {Sai Koti Reddy Danda and Prashanth L. A. and Shalabh Bhatnagar}, title = {Improved Hessian estimation for adaptive random directions stochastic approximation}, booktitle = {55th {IEEE} Conference on Decision and Control, {CDC} 2016, Las Vegas, NV, USA, December 12-14, 2016}, pages = {3682--3687}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/CDC.2016.7798823}, doi = {10.1109/CDC.2016.7798823}, timestamp = {Sat, 09 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/cdc/ReddyAB16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/AJFMS16, author = {Prashanth L. A. and Cheng Jie and Michael C. Fu and Steven I. Marcus and Csaba Szepesv{\'{a}}ri}, editor = {Maria{-}Florina Balcan and Kilian Q. Weinberger}, title = {Cumulative Prospect Theory Meets Reinforcement Learning: Prediction and Control}, booktitle = {Proceedings of the 33nd International Conference on Machine Learning, {ICML} 2016, New York City, NY, USA, June 19-24, 2016}, series = {{JMLR} Workshop and Conference Proceedings}, volume = {48}, pages = {1406--1415}, publisher = {JMLR.org}, year = {2016}, url = {http://proceedings.mlr.press/v48/la16.html}, timestamp = {Wed, 20 Nov 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icml/AJFMS16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/HuAGS16, author = {Xiaowei Hu and Prashanth L. A. and Andr{\'{a}}s Gy{\"{o}}rgy and Csaba Szepesv{\'{a}}ri}, title = {(Bandit) Convex Optimization with Biased Noisy Gradient Oracles}, journal = {CoRR}, volume = {abs/1609.07087}, year = {2016}, url = {http://arxiv.org/abs/1609.07087}, eprinttype = {arXiv}, eprint = {1609.07087}, timestamp = {Tue, 15 Feb 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/HuAGS16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/GopalanAFM16, author = {Aditya Gopalan and Prashanth L. A. and Michael C. Fu and Steven I. Marcus}, title = {Weighted bandits or: How bandits learn distorted values that are not expected}, journal = {CoRR}, volume = {abs/1611.10283}, year = {2016}, url = {http://arxiv.org/abs/1611.10283}, eprinttype = {arXiv}, eprint = {1611.10283}, timestamp = {Wed, 20 Nov 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/GopalanAFM16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jota/BhatnagarA15, author = {Shalabh Bhatnagar and Prashanth L. A.}, title = {Simultaneous Perturbation Newton Algorithms for Simulation Optimization}, journal = {J. Optim. Theory Appl.}, volume = {164}, number = {2}, pages = {621--643}, year = {2015}, url = {https://doi.org/10.1007/s10957-013-0507-1}, doi = {10.1007/S10957-013-0507-1}, timestamp = {Sat, 09 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/jota/BhatnagarA15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/simulation/APDBD15, author = {Prashanth L. A. and H. L. Prasad and Nirmit Desai and Shalabh Bhatnagar and Gargi Dasgupta}, title = {Simultaneous perturbation methods for adaptive labor staffing in service systems}, journal = {Simul.}, volume = {91}, number = {5}, pages = {432--455}, year = {2015}, url = {https://doi.org/10.1177/0037549715581198}, doi = {10.1177/0037549715581198}, timestamp = {Sat, 09 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/simulation/APDBD15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaai/KordaAM15, author = {Nathaniel Korda and Prashanth L. A. and R{\'{e}}mi Munos}, editor = {Blai Bonet and Sven Koenig}, title = {Fast Gradient Descent for Drifting Least Squares Regression, with Application to Bandits}, booktitle = {Proceedings of the Twenty-Ninth {AAAI} Conference on Artificial Intelligence, January 25-30, 2015, Austin, Texas, {USA}}, pages = {2708--2714}, publisher = {{AAAI} Press}, year = {2015}, url = {https://doi.org/10.1609/aaai.v29i1.9619}, doi = {10.1609/AAAI.V29I1.9619}, timestamp = {Mon, 18 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/aaai/KordaAM15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/atal/PrasadAB15, author = {H. L. Prasad and Prashanth L. A. and Shalabh Bhatnagar}, editor = {Gerhard Weiss and Pinar Yolum and Rafael H. Bordini and Edith Elkind}, title = {Two-Timescale Algorithms for Learning Nash Equilibria in General-Sum Stochastic Games}, booktitle = {Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems, {AAMAS} 2015, Istanbul, Turkey, May 4-8, 2015}, pages = {1371--1379}, publisher = {{ACM}}, year = {2015}, url = {http://dl.acm.org/citation.cfm?id=2773328}, timestamp = {Tue, 08 Mar 2022 10:12:47 +0100}, biburl = {https://dblp.org/rec/conf/atal/PrasadAB15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/KordaA15, author = {Nathaniel Korda and Prashanth L. A.}, editor = {Francis R. Bach and David M. Blei}, title = {On {TD(0)} with function approximation: Concentration bounds and a centered variant with exponential convergence}, booktitle = {Proceedings of the 32nd International Conference on Machine Learning, {ICML} 2015, Lille, France, 6-11 July 2015}, series = {{JMLR} Workshop and Conference Proceedings}, volume = {37}, pages = {626--634}, publisher = {JMLR.org}, year = {2015}, url = {http://proceedings.mlr.press/v37/korda15.html}, timestamp = {Wed, 29 May 2019 08:41:45 +0200}, biburl = {https://dblp.org/rec/conf/icml/KordaA15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/AB15, author = {Prashanth L. A. and Shalabh Bhatnagar}, title = {Adaptive system optimization using (simultaneous) random directions stochastic approximation}, journal = {CoRR}, volume = {abs/1502.05577}, year = {2015}, url = {http://arxiv.org/abs/1502.05577}, eprinttype = {arXiv}, eprint = {1502.05577}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/AB15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/ACFM15, author = {Prashanth L. A. and Cheng Jie and Michael C. Fu and Steven I. Marcus}, title = {Cumulative Prospect Theory Meets Reinforcement Learning: Estimation and Control}, journal = {CoRR}, volume = {abs/1506.02632}, year = {2015}, url = {http://arxiv.org/abs/1506.02632}, eprinttype = {arXiv}, eprint = {1506.02632}, timestamp = {Wed, 20 Nov 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/ACFM15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/APBC15, author = {Prashanth L. A. and H. L. Prasad and Shalabh Bhatnagar and Prakash Chandra}, title = {A constrained optimization perspective on actor critic algorithms and application to network routing}, journal = {CoRR}, volume = {abs/1507.07984}, year = {2015}, url = {http://arxiv.org/abs/1507.07984}, eprinttype = {arXiv}, eprint = {1507.07984}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/APBC15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/winet/ACB14, author = {Prashanth L. A. and Abhranil Chatterjee and Shalabh Bhatnagar}, title = {Two timescale convergent Q-learning for sleep-scheduling in wireless sensor networks}, journal = {Wirel. Networks}, volume = {20}, number = {8}, pages = {2589--2604}, year = {2014}, url = {https://doi.org/10.1007/s11276-014-0762-6}, doi = {10.1007/S11276-014-0762-6}, timestamp = {Sat, 09 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/winet/ACB14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/alt/A14, author = {Prashanth L. A.}, editor = {Peter Auer and Alexander Clark and Thomas Zeugmann and Sandra Zilles}, title = {Policy Gradients for CVaR-Constrained MDPs}, booktitle = {Algorithmic Learning Theory - 25th International Conference, {ALT} 2014, Bled, Slovenia, October 8-10, 2014. Proceedings}, series = {Lecture Notes in Computer Science}, volume = {8776}, pages = {155--169}, publisher = {Springer}, year = {2014}, url = {https://doi.org/10.1007/978-3-319-11662-4\_12}, doi = {10.1007/978-3-319-11662-4\_12}, timestamp = {Sun, 25 Oct 2020 22:46:29 +0100}, biburl = {https://dblp.org/rec/conf/alt/A14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cdc/FonteneauA14, author = {Raphael Fonteneau and Prashanth L. A.}, title = {Simultaneous perturbation algorithms for batch off-policy search}, booktitle = {53rd {IEEE} Conference on Decision and Control, {CDC} 2014, Los Angeles, CA, USA, December 15-17, 2014}, pages = {2622--2627}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/CDC.2014.7039790}, doi = {10.1109/CDC.2014.7039790}, timestamp = {Fri, 04 Mar 2022 13:29:15 +0100}, biburl = {https://dblp.org/rec/conf/cdc/FonteneauA14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/comsnets/ACB14, author = {Prashanth L. A. and Abhranil Chatterjee and Shalabh Bhatnagar}, title = {Adaptive sleep-wake control using reinforcement learning in sensor networks}, booktitle = {Sixth International Conference on Communication Systems and Networks, {COMSNETS} 2014, Bangalore, India, January 6-10, 2014}, pages = {1--8}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/COMSNETS.2014.6734874}, doi = {10.1109/COMSNETS.2014.6734874}, timestamp = {Sat, 09 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/comsnets/ACB14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/pkdd/AKM14, author = {Prashanth L. A. and Nathaniel Korda and R{\'{e}}mi Munos}, editor = {Toon Calders and Floriana Esposito and Eyke H{\"{u}}llermeier and Rosa Meo}, title = {Fast {LSTD} Using Stochastic Approximation: Finite Time Analysis and Application to Traffic Control}, booktitle = {Machine Learning and Knowledge Discovery in Databases - European Conference, {ECML} {PKDD} 2014, Nancy, France, September 15-19, 2014. Proceedings, Part {II}}, series = {Lecture Notes in Computer Science}, volume = {8725}, pages = {66--81}, publisher = {Springer}, year = {2014}, url = {https://doi.org/10.1007/978-3-662-44851-9\_5}, doi = {10.1007/978-3-662-44851-9\_5}, timestamp = {Thu, 31 Oct 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/pkdd/AKM14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/PrasadAB14, author = {H. L. Prasad and Prashanth L. A. and Shalabh Bhatnagar}, title = {Algorithms for Nash Equilibria in General-Sum Stochastic Games}, journal = {CoRR}, volume = {abs/1401.2086}, year = {2014}, url = {http://arxiv.org/abs/1401.2086}, eprinttype = {arXiv}, eprint = {1401.2086}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/PrasadAB14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/FonteneauA14, author = {Raphael Fonteneau and Prashanth L. A.}, title = {Simultaneous Perturbation Algorithms for Batch Off-Policy Search}, journal = {CoRR}, volume = {abs/1403.4514}, year = {2014}, url = {http://arxiv.org/abs/1403.4514}, eprinttype = {arXiv}, eprint = {1403.4514}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/FonteneauA14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/AG14, author = {Prashanth L. A. and Mohammad Ghavamzadeh}, title = {Actor-Critic Algorithms for Risk-Sensitive Reinforcement Learning}, journal = {CoRR}, volume = {abs/1403.6530}, year = {2014}, url = {http://arxiv.org/abs/1403.6530}, eprinttype = {arXiv}, eprint = {1403.6530}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/AG14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/A14a, author = {Prashanth L. A.}, title = {Policy Gradients for CVaR-Constrained MDPs}, journal = {CoRR}, volume = {abs/1405.2690}, year = {2014}, url = {http://arxiv.org/abs/1405.2690}, eprinttype = {arXiv}, eprint = {1405.2690}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/A14a.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/KordaP14, author = {Nathaniel Korda and Prashanth L. A.}, title = {On {TD(0)} with function approximation: Concentration bounds and a centered variant with exponential convergence}, journal = {CoRR}, volume = {abs/1411.3224}, year = {2014}, url = {http://arxiv.org/abs/1411.3224}, eprinttype = {arXiv}, eprint = {1411.3224}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/KordaP14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/atal/AnanthapadmanabharaoPDB13, author = {Prashanth Lakshmanrao Ananthapadmanabharao and Horabailu Laxminarayana Prasad and Nirmit Desai and Shalabh Bhatnagar}, editor = {Maria L. Gini and Onn Shehory and Takayuki Ito and Catholijn M. Jonker}, title = {Mechanisms for hostile agents with capacity constraints}, booktitle = {International conference on Autonomous Agents and Multi-Agent Systems, {AAMAS} '13, Saint Paul, MN, USA, May 6-10, 2013}, pages = {659--666}, publisher = {{IFAAMAS}}, year = {2013}, url = {http://dl.acm.org/citation.cfm?id=2485024}, timestamp = {Thu, 09 Sep 2021 16:09:54 +0200}, biburl = {https://dblp.org/rec/conf/atal/AnanthapadmanabharaoPDB13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/LAG13, author = {Prashanth L. A. and Mohammad Ghavamzadeh}, editor = {Christopher J. C. Burges and L{\'{e}}on Bottou and Zoubin Ghahramani and Kilian Q. Weinberger}, title = {Actor-Critic Algorithms for Risk-Sensitive MDPs}, booktitle = {Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States}, pages = {252--260}, year = {2013}, url = {https://proceedings.neurips.cc/paper/2013/hash/eb163727917cbba1eea208541a643e74-Abstract.html}, timestamp = {Mon, 16 May 2022 15:41:51 +0200}, biburl = {https://dblp.org/rec/conf/nips/LAG13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/PrashanthKM13, author = {Prashanth L. A. and Nathaniel Korda and R{\'{e}}mi Munos}, title = {Analysis of stochastic approximation for efficient least squares regression and {LSTD}}, journal = {CoRR}, volume = {abs/1306.2557}, year = {2013}, url = {http://arxiv.org/abs/1306.2557}, eprinttype = {arXiv}, eprint = {1306.2557}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/PrashanthKM13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/KordaPM13, author = {Nathaniel Korda and Prashanth L. A. and R{\'{e}}mi Munos}, title = {Online gradient descent for least squares regression: Non-asymptotic bounds and application to bandits}, journal = {CoRR}, volume = {abs/1307.3176}, year = {2013}, url = {http://arxiv.org/abs/1307.3176}, eprinttype = {arXiv}, eprint = {1307.3176}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/KordaPM13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/AnanthapadmanabharaoCB13, author = {Prashanth Lakshmanrao Ananthapadmanabharao and Abhranil Chatterjee and Shalabh Bhatnagar}, title = {Reinforcement Learning for Sleep-Wake Scheduling in Sensor Networks}, journal = {CoRR}, volume = {abs/1312.7292}, year = {2013}, url = {http://arxiv.org/abs/1312.7292}, eprinttype = {arXiv}, eprint = {1312.7292}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/AnanthapadmanabharaoCB13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/PrashanthPDBD13, author = {Prashanth L. A. and H. L. Prasad and Nirmit Desai and Shalabh Bhatnagar and Gargi Dasgupta}, title = {Simultaneous Perturbation Methods for Adaptive Labor Staffing in Service Systems}, journal = {CoRR}, volume = {abs/1312.7430}, year = {2013}, url = {http://arxiv.org/abs/1312.7430}, eprinttype = {arXiv}, eprint = {1312.7430}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/PrashanthPDBD13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tvt/PrashanthB12, author = {Prashanth L. A. and Shalabh Bhatnagar}, title = {Threshold Tuning Using Stochastic Optimization for Graded Signal Control}, journal = {{IEEE} Trans. Veh. Technol.}, volume = {61}, number = {9}, pages = {3865--3880}, year = {2012}, url = {https://doi.org/10.1109/TVT.2012.2209904}, doi = {10.1109/TVT.2012.2209904}, timestamp = {Sat, 09 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tvt/PrashanthB12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tits/PrashanthB11, author = {Prashanth L. A. and Shalabh Bhatnagar}, title = {Reinforcement Learning With Function Approximation for Traffic Signal Control}, journal = {{IEEE} Trans. Intell. Transp. Syst.}, volume = {12}, number = {2}, pages = {412--421}, year = {2011}, url = {https://doi.org/10.1109/TITS.2010.2091408}, doi = {10.1109/TITS.2010.2091408}, timestamp = {Sat, 09 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tits/PrashanthB11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icsoc/PrashanthPDBD11, author = {Prashanth L. A. and H. L. Prasad and Nirmit Desai and Shalabh Bhatnagar and Gargi Banerjee Dasgupta}, editor = {Gerti Kappel and Zakaria Maamar and Hamid R. Motahari Nezhad}, title = {Stochastic Optimization for Adaptive Labor Staffing in Service Systems}, booktitle = {Service-Oriented Computing - 9th International Conference, {ICSOC} 2011, Paphos, Cyprus, December 5-8, 2011 Proceedings}, series = {Lecture Notes in Computer Science}, volume = {7084}, pages = {487--494}, publisher = {Springer}, year = {2011}, url = {https://doi.org/10.1007/978-3-642-25535-9\_33}, doi = {10.1007/978-3-642-25535-9\_33}, timestamp = {Sat, 09 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icsoc/PrashanthPDBD11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/itsc/AB11, author = {Prashanth L. A. and Shalabh Bhatnagar}, title = {Reinforcement learning with average cost for adaptive control of traffic lights at intersections}, booktitle = {14th International {IEEE} Conference on Intelligent Transportation Systems, {ITSC} 2011, Washington, DC, USA, October 5-7, 2011}, pages = {1640--1645}, publisher = {{IEEE}}, year = {2011}, url = {https://doi.org/10.1109/ITSC.2011.6082823}, doi = {10.1109/ITSC.2011.6082823}, timestamp = {Sat, 09 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/itsc/AB11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ccnc/ADG08, author = {Prashanth L. A. and Sajal Kumar Das and K. Gopinath}, title = {{MAC} Design for Heterogeneous Application Support in {OFDM} Based Wireless Systems}, booktitle = {5th {IEEE} Consumer Communications and Networking Conference, {CCNC} 2008, Las Vegas, NV, USA, January 10-12, 2008}, pages = {412--413}, publisher = {{IEEE}}, year = {2008}, url = {https://doi.org/10.1109/ccnc08.2007.98}, doi = {10.1109/CCNC08.2007.98}, timestamp = {Mon, 09 Aug 2021 14:54:01 +0200}, biburl = {https://dblp.org/rec/conf/ccnc/ADG08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/comsware/PrashanthG08, author = {Prashanth L. A. and K. Gopinath}, editor = {Sunghyun Choi and Jim Kurose and Krithi Ramamritham}, title = {{OFDM-MAC} algorithms and their impact on {TCP} performance in next generation mobile networks}, booktitle = {Proceedings of the Third International Conference on COMmunication System softWAre and MiddlewaRE {(COMSWARE} 2008), January 5-10, 2008, Bangalore, India}, pages = {133--140}, publisher = {{IEEE}}, year = {2008}, url = {https://doi.org/10.1109/COMSWA.2008.4554395}, doi = {10.1109/COMSWA.2008.4554395}, timestamp = {Thu, 04 Nov 2021 14:40:53 +0100}, biburl = {https://dblp.org/rec/conf/comsware/PrashanthG08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.