Zap Q-learning AM Devraj, S Meyn Advances in Neural Information Processing Systems 30, 2017 | 103 | 2017 |
Fastest convergence for Q-learning AM Devraj, SP Meyn arXiv preprint arXiv:1707.03770, 2017 | 46 | 2017 |
Explicit mean-square error bounds for monte-carlo and linear stochastic approximation S Chen, A Devraj, A Busic, S Meyn International Conference on Artificial Intelligence and Statistics, 4173-4183, 2020 | 38 | 2020 |
Reinforcement learning for control of building HVAC systems NS Raman, AM Devraj, P Barooah, SP Meyn 2020 American Control Conference (ACC), 2326-2332, 2020 | 35 | 2020 |
Model-free primal-dual methods for network optimization with application to real-time optimal power flow Y Chen, A Bernstein, A Devraj, S Meyn 2020 American Control Conference (ACC), 3140-3147, 2020 | 32 | 2020 |
Fundamental design principles for reinforcement learning algorithms AM Devraj, A Bušić, S Meyn Handbook of Reinforcement Learning and Control, 75-137, 2021 | 20 | 2021 |
The ODE method for asymptotic statistics in stochastic approximation and reinforcement learning V Borkar, S Chen, A Devraj, I Kontoyiannis, S Meyn arXiv preprint arXiv:2110.14427, 2021 | 18 | 2021 |
Zap Q-Learning with nonlinear function approximation S Chen, AM Devraj, F Lu, A Busic, S Meyn Advances in Neural Information Processing Systems 33, 16879-16890, 2020 | 18 | 2020 |
Learning techniques for feedback particle filter design A Radhakrishnan, A Devraj, S Meyn 2016 IEEE 55th Conference on Decision and Control (CDC), 5453-5459, 2016 | 17 | 2016 |
Differential TD learning for value function approximation AM Devraj, SP Meyn Decision and Control (CDC), 2016 IEEE 55th Conference on, 6347-6354, 2016 | 16 | 2016 |
On matrix momentum stochastic approximation and applications to Q-learning AM Devraj, A Bušić, S Meyn 2019 57th Annual Allerton Conference on Communication, Control, and …, 2019 | 15* | 2019 |
Zap Q-Learning-a user's guide AM Devraj, A Bušić, S Meyn 2019 Fifth Indian Control Conference (ICC), 10-15, 2019 | 15 | 2019 |
Stochastic variance reduced primal dual algorithms for empirical composition optimization AM Devraj, J Chen Advances in Neural Information Processing Systems 32, 2019 | 14 | 2019 |
Q-learning with uniformly bounded variance AM Devraj, SP Meyn IEEE Transactions on Automatic Control 67 (11), 5948-5963, 2021 | 13 | 2021 |
Q-learning with uniformly bounded variance: Large discounting is not a barrier to fast learning AM Devraj, SP Meyn arXiv preprint arXiv:2002.10301, 2020 | 13 | 2020 |
Differential temporal difference learning AM Devraj, I Kontoyiannis, SP Meyn IEEE Transactions on Automatic Control 66 (10), 4652-4667, 2020 | 11 | 2020 |
Accelerating optimization and reinforcement learning with quasi stochastic approximation S Chen, A Devraj, A Bernstein, S Meyn 2021 American Control Conference (ACC), 1965-1972, 2021 | 10 | 2021 |
Power allocation in energy harvesting sensors with ARQ: A convex optimization approach AM Devraj, MK Sharma, CR Murthy 2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP …, 2014 | 10 | 2014 |
Zap Q-Learning for optimal stopping S Chen, AM Devraj, A Bušić, S Meyn 2020 American Control Conference (ACC), 3920-3925, 2020 | 9 | 2020 |
Zap q-learning with nonlinear function approximation S Chen, AM Devraj, F Lu, A Bušić, SP Meyn arXiv preprint arXiv:1910.05405, 2019 | 9 | 2019 |