Decentralized learning for multiplayer multiarmed bandits D Kalathil, N Nayyar, R Jain IEEE Transactions on Information Theory 60 (4), 2331-2345, 2014 | 238 | 2014 |
On regret-optimal learning in decentralized multiplayer multiarmed bandits N Nayyar, D Kalathil, R Jain IEEE Transactions on Control of Network Systems 5 (1), 597-606, 2016 | 83 | 2016 |
Optimal decentralized control with asymmetric one-step delayed information sharing N Nayyar, D Kalathil, R Jain IEEE Transactions on Control of Network Systems 5 (1), 653-663, 2016 | 33 | 2016 |
On a restless multi-armed bandit problem with non-identical arms N Nayyar, Y Gai, B Krishnamachari 2011 49th Annual Allerton Conference on Communication, Control, and …, 2011 | 13 | 2011 |
Optimal decentralized control in unidirectional one-step delayed sharing pattern with partial output feedback N Nayyar, D Kalathil, R Jain 2014 American Control Conference, 1906-1911, 2014 | 6 | 2014 |
Multi-player multi-armed bandits: Decentralized learning with IID rewards D Kalathil, N Nayyar, R Jain 2012 50th Annual Allerton Conference on Communication, Control, and …, 2012 | 6 | 2012 |
Optimal decentralized control in unidirectional one-step delayed sharing pattern N Nayyar, D Kalathil, R Jain 2013 51st Annual Allerton Conference on Communication, Control, and …, 2013 | 4 | 2013 |
Decentralized online learning for optimal matching of users to network resources D Kalathil, N Nayyar, R Jain Proc. INFOCOM, 2012 | 2 | 2012 |
Learning and Control in Decentralized Stochastic Systems N Nayyar University of Southern California, 2015 | | 2015 |
Thoracic Epidural Analgesia Does Not Require Prolonged Urinary Catheterization S Kotova, V Sah, N Nayyar, R Jain Journal of Surgical Research 2 (186), 496, 2014 | | 2014 |
On Confidence Interval Estimation for Hypergeometric Distributions N Nayyar | | |
DECENTRALIZED LEARNING FOR MULTI-PLAYER MULTI-ARMED BANDITS: AN AL-GORITHM FOR NEAR-LOGARITHMIC REGRET D Kalathil, N Nayyar, R Jain | | |