A. M. Devraj, B. Van Roy, and K. Xu, “A Bit Better? Quantifying Information in Bandit Learning.”
S. Chen, A. M. Devraj, A. Bernstein, and S. P. Meyn, “Accelerating Optimization and Reinforcement Learning with Quasi-Stochastic Approximation.”
A. M. Devraj and S. P. Meyn, “Fastest Convergence for Q-learning.”
A. M. Devraj, and S. P. Meyn, “Q-learning with Uniformly Bounded Variance: Large Discounting is Not a Barrier to Fast Learning” To appear in IEEE Transactions on Automatic Control (TAC). Sumitted in July, 2020.
A.M.Devraj,I.Kontoyiannis,andS.P.Meyn,“Differential Temporal Difference Learning.” IEEE Transactions on Automatic Control (TAC). October, 2020.
A. M. Devraj, I. Kontoyiannis, and S. P. Meyn, “Geometric Ergodicity in a Weighted Sobolev Space.” Annals of Probability. January, 2020.
A. M. Devraj, A. Busic, and S. P. Meyn, “Fundamental Design Principles for Reinforcement Learning Algorithms.” Handbook on Reinforcement Learning and Control, Springer Studies in System, Decision and Control. June, 2021.
A. M. Devraj, “Reinforcement Learning Design with Optimal Learning Rate.” PhD thesis, University of Florida. December, 2019.
S. Chen, A. M. Devraj, F. Lu, A. Busic, and S. P. Meyn, “Zap Q-learning with Nonlinear Function Approximation.” Advances in Neural Information Processing Systems (NeurIPS). December, 2020.
S. Chen, A. M. Devraj, A. Busic, and S. P. Meyn, “Explicit Mean-Square Error Bounds for Monte-Carlo and Linear Stochastic Approximation.” International Conference on Artificial Intelligence and Statistics (AISTATS). June, 2020.
A. M. Devraj, and J. Chen, “Stochastic Variance Reduced Primal-Dual Algorithms for Empirical Composition Optimization.” Advances in Neural Information Processing Systems (NeurIPS). December, 2019.
A. M. Devraj, and S. P. Meyn, “Zap Q-learning.” Advances in Neural Information Processing Systems (NeurIPS). December, 2017.
S. Chen, A. M. Devraj, A. Busic, and S. P. Meyn, “Zap Q-Learning for Optimal Stopping Time Problems.” IEEE American Control Conference (ACC). July, 2020.
Y. Chen, A. Bernstein, A. M. Devraj, and S. P. Meyn, “Model-Free Primal-Dual Methods for Network Optimization with Application to Real-Time Optimal Power Flow.” IEEE American Control Conference (ACC). July, 2020.
N. S. Raman, A. M. Devraj, P. Barooah, and S. P. Meyn, “Reinforcement Learning for Control of Building HVAC Systems.” IEEE American Control Conference (ACC). July, 2020.
A. M. Devraj, A. Busic, and S. P. Meyn, “Optimal Matrix Momentum Stochastic Approximation and Applications to Q-learning.” 57th Annual Allerton Conference. September, 2019.
A. M. Devraj, A. Busic, and S. P. Meyn, “Zap Q-Learning: A Users Guide.” Indian Control Conference (ICC). (Invited Session – Best Student Paper Award). January, 2019.
A. M. Devraj and S. P. Meyn, “Differential TD Learning for Value Function Approximation.” IEEE Conference on Decision and Control (CDC). December, 2016.
A. Radhakrishnan, A. M. Devraj, and S. P. Meyn, “Learning Techniques for Feedback Particle Filter Design.” IEEE Conference on Decision and Control (CDC). December, 2016.
A. M. Devraj, C. Gianelli, and J. Li, “Array Processing with Known Waveform and Steering Vector but Unknown Diagonal Noise Covariance Matrix.” IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP). December, 2015.
A. M. Devraj, M. Sharma and C. R. Murthy, “Power Allocation in Energy Harvesting Sensors with ARQ: A Convex Optimization Approach.” IEEE Global Conference on Signal and Information Processing (GolbalSIP). December, 2014.