Concentration of Cumulative Reward in Markov Decision Processes
B. Sayedana, P. E. Caines and A. Mahajan, "Concentration of Cumulative Reward in Markov Decision Processes," arXiv preprint, arXiv:2411.18551, 2024
CV
Education
- Ph.D in Electrical Engineering, McGill University, 2024 (expected)
- M.S. in Electrical Engineering, McGill University, 2019
- B.S. in Electrical Engineering, University of Isfahan, 2017
Publications
Asymptotic Normality of Cumulative Cost in Linear Quadratic Regulators
B. Sayedana, P. E. Caines and A. Mahajan, "Asymptotic Normality of Cumulative Cost in Linear Quadratic Regulators," 2024 IEEE 63rd Conference on Decision and Control (CDC), Milan, Italy, 2024.
Strong Consistency and Rate of Convergence of Switched Least Squares System Identification for Autonomous Markov Jump Linear Systems
B. Sayedana, M. Afshari, P. E. Caines and A. Mahajan, "Strong Consistency and Rate of Convergence of Switched Least Squares System Identification for Autonomous Markov Jump Linear Systems," in IEEE Transactions on Automatic Control, doi: 10.1109/TAC.2024.3351806
Relative Almost Sure Regret Bounds for Certainty Equivalence Control of Markov Jump Systems
B. Sayedana, M. Afshari, P. E. Caines and A. Mahajan, "Relative Almost Sure Regret Bounds for Certainty Equivalence Control of Markov Jump Systems," 2023 62nd IEEE Conference on Decision and Control (CDC), Singapore, Singapore, 2023, pp. 6629-6634, doi: 10.1109/CDC49753.2023.10383246.
Thompson-Sampling Based Reinforcement Learning for Networked Control of Unknown Linear Systems
B. Sayedana, M. Afshari, P. E. Caines and A. Mahajan, "Thompson-Sampling Based Reinforcement Learning for Networked Control of Unknown Linear Systems," 2022 IEEE 61st Conference on Decision and Control (CDC), Cancun, Mexico, 2022, pp. 723-730, doi: 10.1109/CDC51059.2022.9992565.
Consistency and Rate of Convergence of Switched Least Squares System Identification for Autonomous Markov Jump Linear Systems
B. Sayedana, M. Afshari, P. E. Caines and A. Mahajan, "Consistency and Rate of Convergence of Switched Least Squares System Identification for Autonomous Markov Jump Linear Systems," 2022 IEEE 61st Conference on Decision and Control (CDC), Cancun, Mexico, 2022, pp. 6678-6685, doi: 10.1109/CDC51059.2022.9993169.
Counterexamples on the Monotonicity of Delay Optimal Strategies for Energy Harvesting Transmitters
B. Sayedana and A. Mahajan, "Counterexamples on the Monotonicity of Delay Optimal Strategies for Energy Harvesting Transmitters," in IEEE Wireless Communications Letters, vol. 9, no. 7, pp. 1070-1074, July 2020, doi: 10.1109/LWC.2020.2981066.
Cross-layer communication over fading channels with adaptive decision feedback
B. Sayedana, A. Mahajan and E. Yeh, "Cross-layer communication over fading channels with adaptive decision feedback," 2020 18th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOPT), Volos, Greece, 2020, pp. 1-8.
Talks
Asymptotic Normality of Cumulative Cost in Linear Quadratic Regulators
Conference proceedings talk at IEEE Conference on Decision and Control (CDC), Milan, Italy
Relative Almost Sure Regret Bounds for Certainty Equivalence Control of Markov Jump Systems
Seminar at Informal Systems Seminar (ISS), Montreal, Canada
Relative Almost Sure Regret Bounds for Certainty Equivalence Control of Markov Jump Systems
Seminar at Canadian Mathematical Society Winter Meeting, Montreal, Canada
Thompson-Sampling Based Reinforcement Learning for Networked Control of Unknown Linear Systems
Conference proceedings talk at IEEE Conference on Decision and Control (CDC), Cancun, Mexico
Consistency and Rate of Convergence of switched Least Squares Method for Markov Jump Linear Systems
Conference proceedings talk at IEEE Conference on Decision and Control (CDC), Cancun, Mexico
Cross-layer communication over fading channels with adaptive decision feedback
Conference proceedings talk at International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOPT), Volos, Greece (online due to Covid)
Teaching
- Course Lecturer, McGill University
- ECSE 307 (Linear Systems and Control)
- Teaching Assistant, McGill University
- ECSE 205 (Probability and Random Signals I)
- ECSE 210 (Electric Circuits II)
- ECSE 307 (Linear Systems and Control)
- ECSE 403 (Control)
- ECSE 508 (Multi-Agent Systems)