Shalabh Bhatnagar
Shalabh Bhatnagar
Professor in the Department of Computer Science and Automation, Indian Institute of Science
Verified email at iisc.ac.in - Homepage
TitleCited byYear
Fast gradient-descent methods for temporal-difference learning with linear function approximation
RS Sutton, HR Maei, D Precup, S Bhatnagar, D Silver, C Szepesvári, ...
Proceedings of the 26th Annual International Conference on Machine Learning …, 2009
3972009
Natural actor–critic algorithms
S Bhatnagar, RS Sutton, M Ghavamzadeh, M Lee
Automatica 45 (11), 2471-2482, 2009
3642009
Reinforcement learning with function approximation for traffic signal control
LA Prashanth, S Bhatnagar
IEEE Transactions on Intelligent Transportation Systems 12 (2), 412-421, 2010
1962010
Toward off-policy learning control with function approximation
HR Maei, C Szepesvári, S Bhatnagar, RS Sutton
Proceedings of the 27th International Conference on Machine Learning (ICML …, 2010
1902010
Convergent temporal-difference learning with arbitrary smooth function approximation
S Bhatnagar, D Precup, D Silver, RS Sutton, HR Maei, C Szepesvári
Advances in Neural Information Processing Systems, 1204-1212, 2009
1772009
Incremental natural actor-critic algorithms
S Bhatnagar, M Ghavamzadeh, M Lee, RS Sutton
Advances in neural information processing systems, 105-112, 2008
1342008
Stochastic Recursive Algorithms for Optimization: Simultaneous Perturbation Methods
HLPLAP S.Bhatnagar
Stochastic Recursive Algorithms for Optimization: Simultaneous Perturbation …, 2013
1192013
Two-timescale simultaneous perturbation stochastic approximation using deterministic perturbation sequences
S Bhatnagar, MC Fu, SI Marcus, I Wang
ACM Transactions on Modeling and Computer Simulation (TOMACS) 13 (2), 180-209, 2003
972003
A time aggregation approach to Markov decision processes
XR Cao, Z Ren, S Bhatnagar, M Fu, S Marcus
Automatica 38 (6), 929-943, 2002
832002
Adaptive multivariate three-timescale stochastic approximation algorithms for simulation based optimization
S Bhatnagar
ACM Transactions on Modeling and Computer Simulation (TOMACS) 15 (1), 74-107, 2005
702005
Adaptive Newton-based multivariate smoothed functional algorithms for simulation optimization
S Bhatnagar
ACM Transactions on Modeling and Computer Simulation (TOMACS) 18 (1), 2, 2007
532007
Two-timescale algorithms for simulation optimization of hidden Markov models
S Bhatnagar, MC Fu, SI Marcus, S Bhatnagar
Iie Transactions 33 (3), 245-258, 2001
512001
A two time scale stochastic approximation scheme for simulation based parametric optimization
S Bhatnagar, V Borkar
Probability in the Engineering and Informational Sciences 12, 519-531, 1998
491998
A simultaneous perturbation stochastic approximation-based actor-critic algorithm for Markov decision processes
S Bhatnagar, S Kumar
IEEE Transactions on Automatic Control 49 (4), 592-598, 2004
422004
Optimal structured feedback policies for ABR flow control using two-timescale SPSA
S Bhatnagar, MC Fu, SI Marcus, PJ Fard
IEEE/ACM Transactions on Networking 9 (4), 479-491, 2001
402001
An efficient ad recommendation system for TV programs
S Velusamy, L Gopal, S Bhatnagar, S Varadarajan
Multimedia Systems 14 (2), 73-87, 2008
392008
Multi-agent reinforcement learning for traffic signal control
KJ Prabuchandran, HK AN, S Bhatnagar
17th International IEEE Conference on Intelligent Transportation Systems …, 2014
372014
Multiscale stochastic approximation for parametric optimization of hidden Markov models
S Bhatnagar, VS Borkar
Probability in the Engineering and Informational Sciences 11 (4), 509-522, 1997
371997
A Markov decision process model for capacity expansion and allocation
S Bhatnagar, E Fernández-Gaucherand, MC Fu, Y He, SI Marcus
Proceedings of the 38th IEEE Conference on Decision and Control (Cat. No …, 1999
351999
An actor–critic algorithm with function approximation for discounted cost constrained Markov decision processes
S Bhatnagar
Systems & Control Letters 59 (12), 760-766, 2010
342010
The system can't perform the operation now. Try again later.
Articles 1–20