Jayakumar Subramanian
PUBLICATIONS
AI/ML Conferences
-
"Decentralized actor decentralized critic for multi-agent cooperative environments", Subramanian J., Seraj, R., and Mahajan, A., under preparation.
-
"Approximate information state for partially observed systems", Subramanian J. and Mahajan A., The Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM), Montreal, Canada, Jul 7–10, 2019.
-
"Reinforcement learning for mean-field teams ", Subramanian J., Seraj, R., and Mahajan, A., The Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM), Montreal, Canada, Jul 7–10, 2019.
-
"Reinforcement learning in stationary mean-field games", Subramanian J. and Mahajan A., International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Montreal, Canada, 13-17 May, 2019.
AI/ML Workshops
-
"Mean-field games between teams", Subramanian J., Kumar A., and Mahajan, A., 11th Workshop on Dynamic Games in Management Science, Montreal, Canada, Oct 24–25, 2019.
-
"Reinforcement learning for mean-field teams ", Subramanian J., Seraj, R., and Mahajan, A., AAMAS Workshop on Adaptive and Learning Agents, Montreal Canada, 13-17 May, 2019.
-
"A policy gradient algorithm to compute boundedly rational stationary mean field equilibria ", Subramanian J. and Mahajan A., Proceedings of the ICML/IJCAI/AAMAS Workshop on Planning and Learning (PAL-18), Stockholm, Sweden, July 15, 2018.
Control theory Conferences
-
"Approximate information state for partially observed systems", Subramanian J. and Mahajan A., IEEE Conference on Decision and Control (CDC), Nice, France, Dec 11–13, 2019.
-
"Renewal Monte Carlo: Renewal theory based reinforcement learning", Subramanian J., and Mahajan, A., IEEE Conference on Decision and Control (CDC), Miami, Florida, Dec 17–19, 2018.
-
"On controllability of leader-follower dynamics over a directed graph", Subramanian J., Mahajan A., and Paranjape A.A., IEEE Conference on Decision and Control (CDC), Miami, Florida, Dec 17–19, 2018.
-
"Stochastic approximation based methods for computing the optimal thresholds in remote-state estimation with packet drops", Chakravorty, J., Subramanian, J. and Mahajan, A., American Control Conference (ACC), Seattle, WA, May 24–26, 2017.
Journal Publications
-
"Renewal Monte Carlo: Renewal theory based reinforcement learning", Subramanian J., and Mahajan, A., submitted to IEEE Transactions on Automatic Control, 2019.
-
"On the Link Between Weighted Least-Squares and Limiters Used in Higher-Order Reconstructions for Finite Volume Computations of Hyperbolic Equations", (with Prof. J.C. Mandal) in Applied Numerical Mathematics, 05/2008; 58(5):705-725
-
"High Resolution Finite Volume Computations Using A Novel Weighted Least-Squares Formulation" (with Prof. J.C. Mandal and S Rao) in International Journal of Numerical Methods in Fluids, 03/2008; 56(8):1425 - 1431
Patent Applied For
-
"Graph Based Ontology Modelling System", filed in India in August, 2014